Diffusion-Based Image Generation

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 114% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 189

Oct 7, 2026cs.CV

Pooling Representation Autoencoders for Efficient Diffusion

Representation Autoencoders (RAEs) generate images from pre-trained visual fea- tures, but their dense token grids make generative modeling expensive. Motivated by local feature correlations, we introduce PoolDINO, a learned affine pooling operator that merges neighboring tokens. Training the pooling operator jointly with the RGB decoder preserves the standard two-stage RAE procedure without a separate feature auto-encoder. On ImageNet-256, 4x token compression retains comparable generation quality under internal guidance, while 16x compression trades some quality for greater efficiency. At a fixed budget of 100 sampling steps, latent-sampling throughput increases by 3.7x and 9.0x, respectively, relative to the unpooled baseline. Classification and dense prediction evaluations show that comparable guided generation quality can coexist with weaker performance on other tasks.

Ramón Calvo-González, Youssef Saied, François Fleuret

University of Geneva · University of Geneva and Meta

Autoencoders Diffusion-Based Image Generation Diffusion Model Inference Acceleration

Oct 6, 2026cs.CV

Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation

Diffusion Transformers (DiTs) have achieved strong performance in image and video generation, but the quadratic complexity of full attention makes high-resolution generation computationally expensive. Window attention offers an efficient alternative, yet existing methods face a practical trade-off: partitioned window attention typically achieves computational efficiency consistent with its theoretical complexity. However, isolated windows block cross-window interaction, often introducing visible grid-like artifacts in the generated results. Fine-grained sliding-window attention effectively restores interactions across neighboring windows and improves visual quality. However, its irregular computation patterns create a substantial gap between theoretical and practical speedups and require specialized kernels tailored to each hardware backend. To tackle these challenges, we propose BASA, a backend-agnostic sparse attention, which brings the best of both worlds: visual quality and practical acceleration. Specifically, BASA replaces visual self-attention with shifted local-window attention. By introducing a structured window-shifting scheme across DiT blocks, we allow tokens divided by window boundaries in one layer to communicate in the following layers, thereby achieving global information exchange and eliminating window-induced visual artifacts. Notably, our design introduces no additional irregular operators or customized kernels, making it readily deployable on existing attention backends and closing the gap between theoretical sparsity and practical acceleration. Experiments demonstrate that BASA achieves measured speedups exceeding 90% of the theoretical estimates on FLUX and delivers a 4.52

\times

attention speedup on Wan while maintaining competitive generation quality. Codes are publicly available at: https://github.com/lama0110/BASA.

Liao Ma, Jiayi Song, Yunfeng Wu +2

School of Artificial Intelligence, Shanghai Jiao Tong University · School of Data Science, Fudan University · School of Computing and Data Science, The University of Hong Kong

Video Diffusion Models Diffusion Transformer Diffusion-Based Image Generation Sparse Attention Sliding-Window Attention Diffusion Model Inference Acceleration

Oct 6, 2026cs.CV

Two Halves are More than One: Phase-wise Velocity Distillation for Fast and High-Quality Image Generation

Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly. While diffusion distillation techniques can reduce the number of inference steps, high-quality image generation within a single full-backbone-forward compute budget remains challenging. Existing one-step methods typically allocate this budget to a single evaluation of a monolithic student. However, approximating the heterogeneous coarse-to-fine transport with a single monolithic mapping is difficult and often leads to over-smoothed outputs. To address this issue, we propose Phase-wise Velocity Distillation (PVD), which partitions the generation timeline into a coarse and a fine phase, and models the transition within each phase via the average velocity. A dedicated half-sized expert is assigned to each phase, decoupling structural composition from detail refinement while keeping the cumulative computation equivalent to one full-backbone forward pass. We show that the use of two half-sized phase-specific experts outperforms a single full-size monolithic student. On class-conditional image generation, PVD achieves an FID of 1.48 on ImageNet 256 x 256. On more complex text-to-image (T2I) tasks, PVD-distilled models (Stable Diffusion 3.5-Medium, FLUX.1-dev, Qwen-Image) produce results competitive with their multi-step teachers, significantly outperforming prior distillation methods. Moreover, across the evaluated T2I backbones, PVD reduces active parameters by 49.10-50.89% and peak VRAM by 45.76-48.36% compared to the corresponding teachers. Source code and distilled models are available at https://github.com/PolyU-VCLab/PVD.

Zhen Guo, Rongyuan Wu, Qiaosi Yi +3

Department of Computing, The Hong Kong Polytechnic University · OPPO Research Institute

Diffusion Model Distillation Diffusion Distillation Few-Step Diffusion Sampling Diffusion-Based Image Generation T2I Diffusion Models

Oct 5, 2026cs.CV

Level-of-Token Diffusion

Image and video diffusion models allocate equal computation to every region, even when the intended scene calls for varying levels of detail. The spatial distribution of detail can often be anticipated before generation, indicating where computation can be reduced. We introduce Level-of-Token (LoT) Diffusion, a framework that turns this knowledge into an explicit multiresolution token layout (Level-of-Token layout) for adaptive and efficient generation. Tokens represent rectangular patches of varying sizes and shapes, allocating finer tokens where detail is needed and coarser tokens elsewhere. We adapt pretrained diffusion transformers to LoT layouts through a patch-wise asymmetric flow parametrization and embeddings for multiresolution tokens, preserving full-resolution flow prediction at every denoising step while processing only a reduced token sequence. LoT Diffusion enables layout-adaptive generation while preserving pretrained generative priors. We demonstrate LoT with layouts derived from semantic masks, bounding boxes, texture variance, and depth-of-field cues, as well as agentic plans. Across image and video generation, LoT offers favorable quality-efficiency tradeoffs, with significant speedups determined by the layout's token budget. Our project website is at https://georgenakayama.github.io/lotdiffusion/.

Kiyohiro Nakayama, Brian Chao, Jan Ackermann +5

Stanford University · Google

Video Diffusion Models Diffusion Transformer Diffusion-Based Image Generation Diffusion Model Inference Acceleration Visual Token Compression

Oct 4, 2026cs.LG

LiFT: Loop Flow Transformers

We introduce Loop Flow Transformers (LiFT), a family of looped generative models that scales computation by repeatedly applying a shared Diffusion Transformer (DiT) core, with only light changes to the standard architecture. Rather than asking every recurrent step for the final prediction, LiFT trains each step with a single regression target: a point on a straight path from the model's initial estimate to the flow-matching target. Because we index these targets by a continuous depth coordinate, a trained model can loop far beyond its training depth with no retraining, early exits, or other modifications. In our experiments, these longer rollouts improve generation, so inference computation can grow without adding parameters. On ImageNet at 256x256, LiFT-L/2 achieves an FID 3.34 points lower than our dense DiT-XL/2 baseline while using approximately 60% fewer parameters, 32% fewer training FLOPs, and 52% fewer inference FLOPs.

Mohammad Mahdi Derakhshani, Pedro M. P. Curvo, Gertjan J. Burghouts +2

VISLab · University of Amsterdam · TNO, Intelligent Imaging +1

Diffusion Transformer Recurrent Transformers Diffusion-Based Image Generation

Oct 4, 2026cs.LG

FACET: Factorized Asymmetric Conditioning for Efficient Transport in High-Fidelity Fluorescence Microscopy Synthesis

Fluorescence microscopy reveals where proteins localize, but only a limited number of proteins can be imaged in the same cell; generating these images from amino-acid sequence and the cell's morphological context enables in silico localization of unimaged proteins. The two conditions, however, play asymmetric roles: morphological context is spatially aligned with the target, whereas sequence is non-spatial and must specify protein-dependent localization within it, with recurring coarse patterns shared across proteins and finer protein-specific variation. Existing generators condition on both jointly, without separating what each explains. We introduce FACET (Factorized Asymmetric Conditioning for Efficient Transport), a probabilistic generative framework that encodes this structure as an explicit inductive bias: sequence semantics are learned from what context leaves unexplained, coarse localization regularities are shared across proteins through a semantic memory, and protein-specific variation is a bounded residual around them. A variance-preserving state projection further lets FACET perform continuous stochastic transport through a pretrained diffusion predictor with minimal parameter overhead. On held-out proteins, FACET improves spatial overlap by 34.3% on the Human Protein Atlas and 14.0% on OpenCell over a backbone-matched baseline, and reduces FID by 27.2% and 46.5%, respectively, with 75% fewer network evaluations. It also substantially improves protein-association structure recovery and yields better-calibrated predictions, while detailed ablations show complementary contributions from its design choices. These results identify factorized asymmetric conditioning, rather than generator capacity alone, as a key lever for high-fidelity, efficient, and biologically meaningful cellular image synthesis.

Sazan Mahbub, Caleb N. Ellington, Eric P. Xing

Carnegie Mellon University · GenBio AI · Mohamed bin Zayed University of AI

Conditional Image Generation Diffusion-Based Image Generation Conditional Generation

Oct 1, 2026cs.CV

DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation

Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving distribution at extra memory and computation cost. We introduce DMAD, Distribution Matching as Adversarial Distillation, which recasts distribution matching as classification and learns the required log-density ratios directly. Two discriminator heads on a shared backbone distinguish real data and teacher samples from the student's, and linear losses on their logits train the student without auxiliary score fitting. We prove that at the discriminator optimum these losses recover the distribution-matching gradient underlying DMD, through the classical identity linking discriminator logits to log-density ratios. We further introduce gap-based reweighting, which adapts teacher supervision across noise levels from the real-data head's empirical logit gap between real and teacher samples. DMAD reaches a Fréchet Inception Distance (FID) of 1.04 with one-step generation on ImageNet-64x64, 14.47 with four-step SDXL on COCO-10K, and a VBench total score of 85.15 with four-step Wan2.1-T2V-14B, the best values among the compared few-step methods and the multi-step teachers. On MiniMax-H3-33B, our four-step student achieves overall human preference rates of 79.1% over DMD2 and 84.6% over rCM for joint audio-video generation, excluding ties. Our code, models and demos are available at https://yzmblog.github.io/projects/DMAD.

Zhengming Yu, Junkun Yuan, Haotian Yang +8

Texas A&M University · Intelligent Creation, ByteDance

Diffusion Model Distillation Few-Step Diffusion Sampling Diffusion-Based Image Generation Distribution Matching Distillation Adversarial Knowledge Distillation

Sep 30, 2026cs.CV

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff between reconstruction fidelity and generation efficiency: high compression image encoder always increases the learning difficulty of diffusion training, resulting in slow model convergence. Recent representation autoencoders speed up the diffusion training by improving the latent feature's expressive capability by replacing VAE encoders with pretrained semantic encoders, yet they are typically limited to moderate compression and lose pixel-level details necessary for faithful reconstruction. To achieve both high compression and fast diffusion training, we propose DC-SAE, a Decoupled Compact Semantic Autoencoder designed for high-compression image generation with accelerated diffusion model convergence. DC-SAE consists of two key components: (1) a macro-level architecture design that leverages semantic encoders to enable higher compression ratios, and (2) a pixel-level encoder that preserves low-level details, ensuring high-fidelity image reconstruction. We empirically demonstrate that DC-SAE performs strongly on image generation tasks, achieving both compact latent representations and efficient training dynamics. Specifically, on the ImageNet dataset with

512 \times 512

resolution, DC-SAE achieves

32\times

spatial compression, with 29.79 PSNR and 3.37 gFID, substantially outperforming the previous state-of-the-art high-compression tokenizer baselines DC-AE by 13.5% and 54.9% on PSNR and gFID, respectively, maintaining comparable throughput and faster diffusion model training convergence. Beyond class-conditional generation, a

1.6

B-parameter DiT using DC-SAE achieves 0.84 on GenEval and 86.007 on DPG-Bench for text-to-image generation at

1024\times1024

resolution.

Xu Huang, Ye Huang, Zijun Liao +6

Peking University · Singapore University of Technology and Design

Autoencoders Diffusion-Based Image Generation Diffusion Model Acceleration T2I Diffusion Models Visual Token Compression

Sep 29, 2026cs.CV

From Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection

Modern computer vision models achieve high accuracy when trained on large-scale annotated datasets. In critical domains such as construction safety monitoring, data collection is costly, hazardous, and ethically constrained. This paper presents a systematic study comparing two complementary data generation paradigms, (1) Unity Simulation-based rendering and (2) Controllable Diffusion-based generation (CIA), for object detection under real data-scarce conditions. A unified experimental framework enables controlled dataset mixing across real, simulated, and generative sources, while maintaining identical model and training settings. Quantitative evaluation using Precision, Recall, mAP, and custom

Δ

-metrics, reveals that neither simulation nor generative augmentation alone achieves optimal transferability. Unity-only training yields an [email protected] drop of

-50\%

relative to real data, while CIA-only training shows a milder

-16.5\%

degradation. Hybrid compositions significantly improve performance, with the 90% real + 10% Unity configuration achieving the best overall [email protected] of

62.68\%

(

+7.64\%

over baseline), and the 90% real + 10% CIA configuration maximizing precision at

74.45\%

. Results demonstrate that limited synthetic inclusion enhances generalization, while excessive substitution induces domain drift.

Mohamed Benkedadra, Aissa Saoudi, Maxime Gloesener +2

ILIA, Université de Mons Mons, Belgium · Université Polytechnique Hauts-de-France Valenciennes, France · DeepILIA, ILIA, Université de Mons Mons, Belgium +1

Synthetic-to-Real Domain Adaptation Synthetic Data Augmentation Diffusion-Based Image Generation Object Detection

Sep 29, 2026cs.CV

Improved Distributional Diffusion Models

Distributional Diffusion Models (DDMs) replace the standard mean-prediction denoiser with a \emph{distributional} denoiser trained via a scoring rule objective, learning a stochastic approximation to

p(x_1 \mid x_t)

rather than its conditional mean. However, scaling DDMs to modern image-generation settings faces two obstacles: (i) multi-particle training incurs overhead that scales with the number of particles, (ii) DDMs use globally fixed scoring rule hyperparameters, forcing a single trade-off across sampling budgets. We mitigate these limitations by deferring particle expansion to late transformer layers, and the hyperparameter trade-off by introducing time-dependent scoring rule schedules informed by the dynamical regimes of~\citet{Biroli2024}. Combined with a DiT-based latent setup, these changes make DDM training practical on class-conditional ImageNet-

256^2

, achieving 4.48 FID at 4 steps and 2.38 at 50 steps with DiT-XL/2, from a single model trained from scratch in one stage, without a teacher, self-distillation or JVPs. The result is a stochastic few-step generator whose FID does not degrade as the sampling budget grows from 4 to 50 NFE, and the same recipe transfers to text-to-image generation. Code and pre-trained models available at https://github.com/CompVis/iDDM.

Tommaso Martorella, Alexandre Galashov, Felix Krause +4

Munich Center for Machine Learning (MCML) · Google DeepMind

Few-Step Diffusion Sampling Diffusion-Based Image Generation T2I Diffusion Models Diffusion Models

Sep 28, 2026cs.CV

Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers

Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas the models' own representations are often treated as a by-product of synthesis. We ask whether diffusion models can instead be trained to learn substantially stronger semantic representations without sacrificing generation quality. SelfFlow takes a step in this direction by introducing self-supervised patch alignment into flow matching, but its main gains remain in faster convergence and improved generation. Inspired by DINO and iBOT, we extend this framework with cross-view class-token alignment to further strengthen semantic representations. Specifically, we form two independently noised, dual-timestep observations of each image and align each student class-token representation with the stop-gradient EMA-teacher target from the other observation. This objective is optimized jointly with the inherited flow-matching and local patch objectives. Notably, although the additional objective acts only on the class token, it strengthens both class-token and patch representations. Compared with a matched two-view baseline, ImageNet linear-probing accuracy improves by 9.4% using the class token and 10.1% using mean-pooled patch tokens, while frozen-backbone VOC2012 segmentation improves by 3.6 mIoU. These representation gains are achieved while maintaining comparable ImageNet generation FID. In text-to-image training, the same objective also improves generation FID, reducing it from 2.52 to 2.37 at matched checkpoints. Our results show that representation need not remain a by-product of generation or merely a tool for improving it: it can be directly optimized as a first-class capability of diffusion pretraining alongside generation.

Xiaoyu Wu, Yifei Wang, Chen Wei

Carnegie Mellon University · Rice University

Flow Matching Diffusion Transformer Diffusion-Based Image Generation Self-Supervised Visual Representation Learning

Sep 28, 2026cs.CV

Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion

Pixel-space diffusion Transformers (DiTs) directly operate on high-dimensional visual data, yet their hidden representations typically undergo uniform refinement across depth. Natural images, however, are inherently organized at different levels of granularity. Global structure can often be represented compactly, whereas local textures and fine details require richer representations. Motivated by this, we introduce heterogeneous refinement in pixel-space DiTs, assigning different feature groups distinct refinement budgets across depth. Consequently, an ordered feature specialization emerges: sparsely refined features predominantly encode global visual structure, whereas more frequently refined features increasingly specialize toward localized, high-frequency details. We refer to these two groups as persistent and active features, respectively. Building on this emergent specialization, we introduce Persistence Forcing (PerF), which explicitly exploits this persistent--active feature organization for pixel-space image generation. This enables persistent features to continuously condition actively refined features, allowing stable global information to guide the ongoing refinement of finer visual details. During generative sampling, this interaction further induces a meaningful guidance direction that promotes coherent global structure and naturally complements classifier-free guidance. On ImageNet

256\times256

, PerF-L achieves FID of

1.91

, approaching

1.86

of JiT-H with only half the parameters, while PerF-H further achieves FID of

1.63

and

1.76

on ImageNet

256\times256

and

512\times512

, respectively.

Chong Wang, Zixuan Fu, Shiqi Huang +3

Nanyang Technological University · KTH Royal Institute of Technology · Hebei University of Technology

Diffusion Transformer Diffusion Guidance Pixel-Space Diffusion Models Diffusion-Based Image Generation Diffusion Models

Sep 27, 2026cs.CV

Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers

In diffusion-based generation, a neural network can be trained to predict the clean data, the noise, or the velocity from a noisy input. These prediction targets are interconvertible and describe the same generative process, yet plain Diffusion Transformers operating on large pixel patches succeed with clean prediction and fail with noise or velocity prediction. We argue that this asymmetry arises because noisy targets require the residual stream to preserve noise-dependent input variation through depth for the final readout, forcing subsequent layers to compute on noisy representations. A spectrally concentrated clean target imposes a lighter demand, leaving greater freedom to organize hidden representations for subsequent computation. We call this preservation requirement residual-stream burden and show how it shapes representation learning in Diffusion Transformers. Controlled experiments indicate that the exploitable structure is spectral concentration in patch space and that the bandwidth of the persistent residual state is a key resource for noisy prediction. We further show that this account is consistent with recent decoupled pixel-space architectures, whose diverse designs all reduce the residual-stream burden on the main pathway. To examine this understanding from a complementary direction, we expand and reorganize the residual-stream bandwidth directly, introducing Spatially Indexed Hyper-Connections (SiHC) that reach FID 1.71 on ImageNet

256^2

. Together, these results identify residual-stream burden as a mechanism through which prediction targets and architecture jointly shape representation learning in Diffusion Transformers.

Tongtong Liang, Siqi Kou, Ziqiao Xi +6

UC San Diego · Shanghai Jiao Tong University · Aether AI

Diffusion Transformer Residual Learning Hyper-Connections Diffusion-Based Image Generation Diffusion Models

Sep 25, 2026cs.CV

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual representations into image generation. However, RAEs still need to decide which encoder layers form the shared latent space for the generator and pixel decoder. This choice involves a trade-off: shallower layers tend to preserve fine pixel details better, while deeper layers tend to yield better generation metrics. A fixed heuristic layer fusion therefore couples two stages that benefit from different information. We introduce FuseReg, which replaces heuristic feature selection with training over random subsets of encoder layers. We theoretically analyze the underlying mechanism: subset sampling preserves the full-layer latent mean in expectation while explicitly penalizing sensitivity to cross-layer disagreement. On ImageNet-256 with DINOv3-L, a single FuseReg decoder reconstructs from full, sparse, and single-layer fusions without retraining, achieving higher PSNR than decoders specialized to fixed fusions. This flexibility also benefits generation: decoder replacement alone reduces unguided gFID by 27% with an unchanged RAEv2 DiT-XL generator. Applying FuseReg to both stages also reduces unguided gFID by 29% on DiT-Base. The reconstruction and generation benefits also extend to other encoder families. FuseReg narrows the reconstruction-generation gap without additional training cost or architectural changes.

Hongyang Du, Yunfei Xie, Junjie Ye +13

USC PSI Lab · Brown University · Rice University +4

Autoencoders Image Reconstruction Diffusion-Based Image Generation Feature Fusion

Sep 21, 2026cs.CV

PixelDiT2: Representation-Grounded Pixel Diffusion Transformers

Recent advances in pixel-space diffusion models have narrowed the image quality gap with latent-space diffusion, but still converge more slowly and lag behind in final image quality. We argue that a key reason is the lack of an explicit representation prior: unlike latent diffusion, which usually denoises in a compact and structured latent space, pixel diffusion needs to learn denoising-friendly representations and pixel generation simultaneously from raw RGB space. To address this problem, we propose PixelDiT2, an end-to-end pixel-space diffusion model designed to decouple representation learning from pixel generation without introducing an autoencoder or latent reconstruction bottleneck. We propose representation grounding that uses a frozen pretrained vision foundation model to provide explicit per-patch representation guidance throughout denoising, allowing the pixel diffusion transformer to focus more on pixel generation. On ImageNet-256x256, PixelDiT2 achieves an FID of 1.46 after 600 epochs; at 512x512 resolution, PixelDiT2 achieves an FID of 1.48 after 680 epochs. Project page: https://pixeldit.github.io/pixeldit2/

Yongsheng Yu, Wei Xiong, Yichen Sheng +2

NVIDIA · University of Rochester

Diffusion Model Guidance Diffusion Transformer Pixel-Space Diffusion Models Diffusion-Based Image Generation

Sep 21, 2026cs.CV

AlignMorph: Tuning-Free Diffusion Image Morphing via Explicit Semantic Transport

Image morphing aims to produce a smooth and semantically consistent transition between two input images. Existing diffusion-based morphing methods either require expensive per-pair optimization or rely on implicit spatial alignment, which easily fails under large layout discrepancies. To address these limitations, we propose AlignMorph, a novel tuning-free diffusion framework guided by the principle of transport-then-denoise. We explicitly decouple geometric alignment from generative denoising to avoid structural entanglement. Our framework consists of two core components. (1) Global Semantic Transport, which achieves diffusion-compatible semantic alignment via entropic optimal transport and reliability-aware latent warping; and (2) Coordinate-Aligned Generation, which uses a symmetric bi-phase attention handoff to maintain consistent spatial coordinates throughout denoising. Without any tuning, AlignMorph effectively eliminates ghosting and achieves superior structural coherence and temporal smoothness on morphing benchmarks. Code is available at https://github.com/51xOne/Alignmorph.

Wuyi Liu, Xu Han, Yuren Chen +3

Huazhong University of Science and Technology · Beijing Jiaotong University · Beihang University +1

Diffusion-Based Image Generation

Sep 20, 2026cs.CV

PhysReflect: Geometry and Perception Guided Diffusion for Physically-Plausible Mirror Reflections

Diffusion models generate high-quality images, yet often violate the physical laws governing mirror reflections. Reflections often suffer from geometric aberrations, including positional offsets, directional misalignment, proportional imbalance, and structural distortion. These failures remain evident even in contemporary state-of-the-art generative systems. Existing methods itigate this problem through synthetic data scaling or auxiliary depth conditioning, yet their merely reliance on latent-space noise reconstruction losses as implicit supervision prevents direct enforcement of reflection-specific geometric and perceptual constraints. To bridge this gap, we present PhysReflect, a geometry and perception guided diffusion framework that decodes the predicted clean latent into pixel space at each training step and applies annealed supervision through two complementary differentiable objectives. The Geometric Loss enforces mirror-induced spatial consistency through sparse epipolar correspondence and dense boundary projection alignment, where a SAM2-based TwinTrack mechanism provides stable in-mirror localization for boundary-aware supervision. The Perceptual Loss preserves reflected appearance by combining Semantic Consistency Loss, which maintains reflected identity and appearance via DINOv2 features, and Lighting Consistency Loss, which regularizes depth, surface-normal, and illumination coherence under monocular geometry priors. Experiments on synthetic and real-world benchmarks show that PhysReflect outperforms prior mirror-reflection methods in geometric, perceptual, and physical-plausibility metrics, as well as qualitative visual results.

Shuheng Ge, Hongwei Ren, Li Zhang +1

Harbin Institute of Technology, Harbin, China

Diffusion Model Guidance Image Generation Diffusion-Based Image Generation

Sep 17, 2026cs.CV

Beyond the Foreground: FOV-Aware Polyp Image Synthesis via Lesion-Guided Adaptive Mucosal Context Propagation

Synthetic image and mask pairs can alleviate scarce colonoscopy annotations, but realistic synthesis requires preserving the supplied lesion while generating compatible mucosa. Existing foreground-guided methods treat all non-foreground pixels as background and rely mainly on local integration. Directly applying them to colonoscopy causes two problems: non-mucosal black regions contaminate generated tissue, and local reasoning produces inconsistent mucosal texture and illumination. We propose LAMP, the first foreground-guided framework for polyp image synthesis based on lesion-guided adaptive mucosal context propagation. LAMP explicitly separates the lesion, valid mucosa, and camera exterior using a field-of-view (FOV) mask. Lesion-to-Mucosa cross-attention extracts lesion appearance conditions for valid-mucosa locations, while FOV-constrained multidirectional Vision Receptance Weighted Key Value propagates them over legal tissue support. An adaptive gate then controls their residual fusion into the diffusion U-Net. Extensive experiments on five polyp datasets demonstrate that LAMP substantially outperforms existing methods in overall generation quality and consistently improves five downstream segmentation models. Our code will be released at https://github.com/wangtong627/LAMP.

Tong Wang, Yuting He, Bin Ren +2

Southeast University · MBZUAI · Case Western Reserve University

Synthetic Data Augmentation Diffusion-Based Image Generation Medical Image Synthesis

Sep 16, 2026cs.LG

Spatially Adaptive Noise Injection

Diffusion samplers reverse a learned noising process using either stochastic (DDPM) or deterministic (DDIM) updates, which represent endpoints of a single family controlled by a scalar noise-injection variance that is applied identically at every spatial location. This uniform approach neglects the geometry of natural images: high-curvature regions such as edges and textures, where the denoiser is uncertain, benefit from stochastic correction, whereas smooth regions, where the score is precise, are degraded by injected noise. This work investigates whether each pixel requires stochastic correction at a given timestep and introduces Spatially Adaptive Noise Injection (SANI), a novel sampling framework that dynamically adjusts noise application on a per-pixel basis. SANI integrates a probabilistic gating mechanism with a derived spatially adaptive variance, ensuring that noise is injected precisely where needed to refine complex features while preserving well-formed structures. Experimental results and decoupling ablations demonstrate that SANI consistently improves Fréchet Inception Distance (FID) over the vanilla DDPM and DDIM endpoint samplers across diverse sampling timesteps, while remaining competitive with variance-learning baselines, highlighting the importance of spatial adaptivity in diffusion sampling.

Frantzeska Lavda, Maciej Falkiewicz, Van Khoa Nguyen +1

University of Applied Sciences Western Switzerland, HES-SO Geneva · Computer Science Department, University of Geneva

Diffusion Sampling Diffusion-Based Image Generation

Sep 3, 2026cs.CV

Mudragen: Geometrically Supervised Generation of Interacting Two-Hand Mudras for Preserving Indian Classical Dance Heritage

Automatic generation of hand gestures is essential for the transmission of Indian classical dance and critical for its preservation. Indian classical dance gesture datasets are inherently low-resource, and the canonical Sanskrit definitions of many mudras lack precise textual descriptions, limiting the effectiveness of conventional text-conditioned image generation models. We present \textbf{MudraGen}, a conditional diffusion framework that synthesizes realistic RGB images of \textit{Samyukta Hasta Mudras} -- interactive two-hand gestures from Bharatanatyam (an Indian classical dance form). Unlike prior work on simple hand signs or single-hand gestures, MudraGen introduces geometry-aware supervision to capture the precise coordination, anatomical validity, and cultural nuance of interacting hands. We formulate three geometry-aware objectives: Keypoint Loss for 3D joint alignment, Joint Offset Loss for inter-hand spatial coherence, and Shape Consistency, which serves as an anatomical regularizer by encouraging consistent hand morphology while allowing independent hand poses. Together, these objectives guide the diffusion model toward anatomically plausible and well-coordinated hand configurations, enabling the synthesis of photorealistic and pose-accurate gesture images. Experimental results show that MudraGen surpasses existing state-of-the-art generative approaches in visual realism, anatomical correctness, and preservation of fine hand-pose structure, enabling faithful reproduction of complex Samyukta Hasta mudras. Beyond quantitative gains, its ability to generate culturally grounded and structurally consistent gestures highlights practical applications in cultural preservation and dance education.

Jagadish Kashinath Kamble, Jayanta Mukhopadhyay, Debaditya Roy +1

Indian Institute of Technology Kharagpur Kharagpur, West Bengal, INDIA · Ashoka University Sonipat, Haryana, INDIA

Conditional Image Generation Human Motion Generation Diffusion-Based Image Generation Cultural Heritage

Sep 2, 2026cs.CV

DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation

Industrial anomaly detection benefits from anomaly samples, yet newly deployed products typically provide only normal images, making anomaly samples difficult to collect. Zero-shot anomaly generation offers a promising solution which avoids collection of target-product anomalies. However, existing methods mainly rely on texture images or text descriptions as anomaly sources, which often produce unrealistic anomalies. Observing that similar anomalies can recur across different products, we propose anomaly transfer-based zero-shot generation, which reuses real anomalies from existing source products, making target-product anomalies no longer necessary to generate realistic anomalious samples for unseen target products. Since not every anomaly type suits the target product, an anomaly type filtering mechanism first selects plausible source types. To transfer selected anomaly, we propose DPA, a diffusion-based framework that decouples product-agnostic anomaly representations. Instead of directly extracting anomaly representations, DPA learns product-irrelevant anomaly embeddings through training with the mismatched data pair, enabling transferable anomaly concept learning across products. Furthermore, we design an adaptive mask-guided pipeline that leverages adaptive masks to control the positional and geometric plausibility of generated anomalies during generation. A training-free anomaly labeling module is further introduced to produce pixel-level annotations aligned with generated anomalies. Extensive experiments on MVTec-AD, VisA, and a dedicated anomaly-transfer benchmark demonstrate that the proposed setting and DPA generate more realistic anomalies and significantly improve downstream anomaly detection performance under both zero-shot and few-shot settings. Source code and models will be released.

Hang Yao, Yansheng Fu, Ming Liu +4

Industrial Anomaly Detection Diffusion-Based Image Generation Synthetic Anomaly Generation

Sep 1, 2026cs.AI

Denoising Diffusion Generative Models Secretly Calculate Attentions

Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer architectures employing attention mechanism. Here, we show that diffusion models also inherently use an attention mechanism very similar to that of transformers. Therefore, attention emerges as a universal machine learning principle, based on a general training objective. We also show similarities in basic functional principle of auto-encoders and attention-based models. These equivalences allows us to interchange these designs based on practical requirements. As an example, we can reformulate the diffusion framework to reduce the lengthy training process and computation-intensive image generation. Using this approach, a simplified algorithm is proposed for image generation which is based on attention mechanism. Results show that the attention-based implementation achieves comparable performance with significantly less effort and computational resources.

Farzan Haddadi, Leila Monfared, Ebrahim Rezaii +3

School of Electrical Engineering, Iran University of Science & Technology, Tehran, IRAN · Independent researcher

Attention Control in Diffusion Models Diffusion-Based Image Generation Diffusion Model Acceleration Diffusion Models

Sep 1, 2026cs.CV

Advanced Pixel Diffusion Model with Guided Sparse Global Refinement

Pixel-space diffusion has recently emerged as a promising direction for high-fidelity image generation by modeling images directly in the original pixel domain. However, pixel-space diffusion is computationally demanding due to the extremely high dimensionality of natural images. For efficiency, existing pixel diffusion models either compromise fine details with large-patch tokenization or confine subsequent refinement within individual patches. Such intra-patch refinement inevitably restricts structural continuity across patch boundaries and long-range token interactions, limiting refinement quality. To address these issues, we propose PixSGR, a novel Pixel diffusion framework with Sparse Global Refinement tailored for modeling the distribution of natural images directly in pixel space. PixSGR starts from a supervised low-channel bottleneck to efficiently capture the low-dimensional manifold of natural images. It then progressively expands the channel dimensionality and spatial resolution to recover increasingly fine-grained structures. At the spatial refinement stage, coarse-scale attention maps preselect globally relevant interactions to pre-sparsify fine-scale attention, enabling non-local refinement beyond isolated patches without the quadratic cost of dense attention. Extensive experiments on ImageNet validate the effectiveness of PixSGR. It achieves an FID of 1.51 at 256

\times

256 and maintains performance when scaled to 512

\times

512, attaining an FID of 1.60.

Weiyi You, Jinhua Zhang, Xingyu Zhou +3

University of Electronic Science and Technology of China

Pixel-Space Diffusion Models Diffusion-Based Image Generation Diffusion Models

Aug 13, 2026cs.AI

From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion

Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a promising solution, existing policies rely on local similarity heuristics, which we identify as being significantly misaligned with final generation quality. This discrepancy stems from the non-uniform propagation and accumulation of errors along the denoising trajectory. To address this, we propose Global-Impact Cache (GCache). We first establish a rigorous theoretical characterization of the error propagation upper bound. Recognizing that this bound can be overly conservative for complex, highly non-convex diffusion models, we further reparameterize the propagation exponent with a Bernstein form and reformulate cache policy search as a bilevel optimization problem. In detail, GCache identifies an optimal reuse policy in the inner objective while aligning the error-weighting function with generation quality loss in the outer objective. This framework effectively reconciles theoretical rigor with empirical performance, learning to prioritize computation where it most impacts visual fidelity. Extensive experiments demonstrate that GCache consistently outperforms prior caching strategies on both video and image generation. Notably, on the state-of-the-art Wan2.1 video diffusion model, GCache maintains a 2.17x speedup while significantly enhancing generation quality, reducing LPIPS from 0.1095 to 0.0316.

Xichen Ye, Yifan Wu, Zhikang Xie +3

College of Computer Science and Artificial Intelligence, Fudan University · Faculty of Engineering, The Chinese University of Hong Kong · School of Data Science, Fudan University

Video Diffusion Models Diffusion-Based Image Generation Diffusion Model Caching Diffusion Model Inference Acceleration Diffusion Models

Aug 11, 2026cs.CV

AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss

Fréchet distance has recently emerged as an effective distribution-level objective for generator post-training, complementing the conventional sample-level diffusion and flow-matching losses. However, directly optimizing Fréchet objectives can cause Fréchet hacking. The target metrics keep improving, but visual quality and Fréchet alignment in other feature spaces may stagnate or deteriorate. We attribute this failure to the static pretrained feature spaces used by existing Fréchet losses. These feature spaces provide incomplete and fixed views of the differences between real and generated distributions. To address this limitation, we propose Adversarial Fréchet Distance (AdvFD), which complements the static representation targets in FD-Loss with a calibrated adversarially learned representation. AdvFD augments the original static Fréchet objective with a learnable representation that adversarially maximizes the Fréchet discrepancy between real and generated samples, while the generator minimizes the same discrepancy in the resulting adaptive feature space. To prevent the adversarial representation from trivially increasing the objective through feature amplification, we further introduce real-feature whitening, which normalizes its scale and covariance geometry and stabilizes the min--max optimization. Extensive experiments show that AdvFD consistently improves one-step generator post-training across both JiT and pMF backbones and across different model scales.

Mingju Gao, Jingkai Zhou, Kun Gai +2

Peking University · KlingAI Research

Diffusion Model Alignment Diffusion Model Fine-Tuning Diffusion-Based Image Generation

Aug 10, 2026cs.CV

Unveiling the Secret of AdaLN-Zero in Diffusion Transformer

Diffusion transformer (DiT), a rapidly emerging architecture for image generation, has gained much attention. However, despite ongoing efforts to improve its performance, the understanding of DiT remains superficial. In this work, we delve into and investigate a critical conditioning mechanism within DiT, adaLN-Zero, which achieves superior performance compared to adaLN. Our work studies three potential elements driving this performance, including an SE-like structure, zero-initialization, and a "gradual" update order, among which zero-initialization is proved to be the most influential. Building on this understanding, we propose an analysis-guided initialization strategy, termed adaLN-Gaussian, which serves both as an empirical validation of our analysis and as a practical initialization method that consistently improves optimization efficiency. On the other hand, inspired by the SE-like structure, we introduce an improved conditioning mechanism called SE-adaLN-Zero. Extensive experiments following DiT on four datasets, especially on ImageNet1K demonstrate the effectiveness and generalization of adaLN-Gaussian and SE-adaLN-Zero. Beyond class-to-image generation, we also evaluate the generalization of the two improved methods on text-to-image generation.

Jie Zhu, Mingyu Ding, Boqiang Duan +2

Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education, China, and School of Computer Science, Peking University, China. · UC Berkeley · Baidu, Beijing, China

Diffusion Transformer Neural Network Initialization Layer Normalization Diffusion-Based Image Generation

Aug 6, 2026cs.CV

InsertFuse: A Unified Framework for Multi-Category Reference-Guided Image Insertion

We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise learning from cross-category capability consolidation. InsertFuse first trains specialized experts for different insertion categories and then introduces Insertion On-Policy Distillation (IOPD) to consolidate their capabilities into a single student. By querying the matched expert at states visited by the student, IOPD preserves category-specific insertion behavior while mitigating the cross-category interference caused by direct joint training. To improve spatial control, we propose Token-Aligned Geometry Conditioning (TAGC), which maps mask-derived geometric cues to the visual token grid, and Region-Balanced Flow Matching, which separately normalizes prediction errors inside and outside the insertion region to prevent background-dominated and scale-dependent supervision. We further introduce Reference CFG to isolate and strengthen the guidance induced by the visual reference under fixed scene and geometry conditions, with IOPD transferring this enhanced supervision into the unified student. Extensive experiments on the public AnyInsertion benchmark and our multi-category test set demonstrate state-of-the-art performance on most metrics, showing strong reference fidelity and generation quality across diverse insertion categories.

Guangzhao Li, Qingyan Wei, Huayu Zheng +7

1Shanghai Jiao Tong University · 2Shanghai Innovation Institute · 4Xi’an Jiaotong University +2

Conditional Image Generation Diffusion-Based Image Generation Knowledge Distillation

Aug 6, 2026cs.CV

Controllable Clothing: Precise Labels and Generation for Virtual Try-On with Latent Diffusion Models

In this technical report, I present a new method for guiding image generation in the context of Virtual- Try-On (VITON). The proposed method leverages new open source Ai models to augment the image data with labels, such as lengths and styles. By training adapters with these labels paired with images of the garments, the model can produce a more diverse set of images that the user can control. For the end user, such as a retailer, this means that they can assure that the produced image is as true to the true fit as possible, not misleading consumers

Max Rehman Linder

PUBLICIS RESOURCES GENAI TEAM · ÉCOLE POLYTECHNIQUE

Virtual Try-On Conditional Image Generation Diffusion-Based Image Generation Controllable Image Generation

Aug 5, 2026eess.IV

A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets

Prenatal ultrasound imaging is key for assessing fetal health, but AI progress is limited by scarce, privacy-restricted, and hard-to-annotate datasets. We propose a high-resolution fetal ultrasound synthesis framework based on the EDM2 diffusion architecture, trained on multiple public datasets to generate 512x512 images across six anatomical classes. Our method achieved improved image quality with lower FID scores and enhanced downstream fetal plane classification, reaching 93.36% ensemble accuracy after fine-tuning, surpassing real-data-only training. Clinical evaluation by an experienced fetal ultrasound specialist (10+ years) on 100 images yielded a mean realism score of 2.67/5, with real images rated higher than synthetic. Artefacts included smoothing, speckle irregularities, and anatomical inconsistencies. Code, data, models and other resources to reproduce this work are available at https://github.com/xfetus/fetal-ultrasound-edm2.

Harvey Mannering, Yilin Zhang, Ziao Liu +3

University of Southampton · Tsinghua University · King’s College London +1

Synthetic Data Augmentation Ultrasound Imaging Diffusion-Based Image Generation Medical Image Synthesis

Aug 5, 2026cs.CV

STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models

On-policy distillation (OPD) has become an effective approach for consolidating multiple task-specialized image generation models into a single student. However, existing OPD methods optimize the student mainly to match the teacher's output velocity, making the teacher the upper limit of the optimization objective. While output-level supervision alone leaves the student's blockwise representation evolution underconstrained, which weakens the transfer of capabilities that must be progressively developed across layers. We propose STEP-OPD, an on-policy distillation framework for image generation that extends the student's learning target beyond the teacher and introduces explicit constraints on its internal representation evolution. Instead of treating the teacher as the final target, we use the velocity difference between each task-specific teacher and the shared base model as a direction for further learning and add a scaled version of this difference to the teacher velocity. In addition, we align the direction and magnitude of representation changes between the student and teacher, enabling the student to learn how representations are progressively transformed across network blocks. Experiments on compositional alignment, text rendering, and human preference show that our method consistently improves Standard OPD methods. In particular, it increases the GenEval score of DiffusionOPD from 0.927 to 0.961, while also improving OCR and all preference-based metrics. The resulting unified student surpasses the corresponding single-task teachers across all three capability groups, showing that output extrapolation enables beyond-teacher learning. And representation change alignment provides complementary guidance for the student's internal transformations.

Qingyan Wei, Guangzhao Li, Xiaobing Tu +5

Shanghai Jiao Tong University · Shanghai Innovation Institute · Alibaba Group

Diffusion Model Distillation Diffusion-Based Image Generation On-Policy Distillation