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

All topics

Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds
Aug 5, 2026Yizhu Wang, Mu Niu, Xiaochen YangLatent Diffusion Models Generative Modeling
School of Mathematics and Statistics, University of Glasgow, Glasgow, U.K.
FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis
Aug 4, 2026Zhang Weihui, Wang Ruizhi, Xu Hongye +3Physics-Informed Generative Modeling Synthetic Data Augmentation
Zhejiang University, Zhejiang, China
IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images
Aug 4, 2026Xiaoyan Feng, Zheng Gao, Tong Guan +4Diffusion Model Watermarking Diffusion-Based Image Generation
1Griffith University · University of New South Wales · 3Zhejiang University
HyperbolicDiffusion: Sharp & Scalable Tiled Generation on the Hyperbolic Plane
Aug 4, 2026Hugo Caselles-DupréDiffusion Sampling Image Generation
Obvious Research Paris, France
DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers
Aug 4, 2026Binglei Li, Mengping Yang, Zhiyu Tan +4Representation Learning Diffusion Transformer
Fudan University, Shanghai, China · Shanghai Academy of AI for Science, Shanghai, China · Shanghai Innovation Institute, Shanghai, China
SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching
Aug 3, 2026Zong-Wei Hong, Jinglun Li, Shen Zhang +3Diffusion Model Alignment Flow Matching
JIIOV Technology
GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation
Aug 3, 2026Jeonghyeok Do, Munchurl KimGeospatial Foundation Models Diffusion-Based Image Generation
Information & Electronics Research Institute KAIST · School of Electrical Engineering KAIST
SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents
Aug 2, 2026Yibin Huang, Jixiang Hong, Zongzhao Li +8Autoencoders Vision Foundation Model Adaptation
Alibaba Group · Gaoling School of Artificial Intelligence, Renmin University of China
UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction
Aug 2, 2026Junno Yun, Yaşar Utku Alçalar, Mehmet AkçakayaToken Merging Diffusion Transformer
University of Minnesota
InstancePin: Instance-Addressable Layout-to-Image Diffusion via Coordinate Pinning
Aug 1, 2026Chaoyue Wu, Yunfei Zhang, Si WuConditional Image Generation Image Generation
School of Computer Science and Engineering, South China University of Technology, Guangzhou, Guangdong, P. R. China · School of Future Technology, South China University of Technology, Guangzhou, Guangdong, P. R. China
OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation
Jul 31, 2026Jinyi Xu, Peng Chen, Yunkang Cao +3Industrial Anomaly Detection Anomaly Localization
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University · School of Artificial Intelligence and Robotics, Hunan University · Department of Computer and Information Science, University of Macau +1
FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference
Jul 30, 2026Hanshuai Cui, Zhiqing Tang, Zhi Yao +3Diffusion-Based Image Generation Diffusion Model Caching
School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai 519087, China
Amortized Moment Matching for Visual Generation
Jul 29, 2026Wenze Liu, Xintao Wang, Pengfei Wan +1One-Step Generative Modeling Distribution Matching
MMLab, CUHK · Work done at Kuaishou Technology. · Kling Team, Kuaishou Technology
LumaGuide: Distribution Shaping for Training-Free HDR Generation in Diffusion Models
Jul 28, 2026Bowen Chen, Shreshth Saini, Balu Adsumilli +1Diffusion Model Guidance Image Generation
The University of Texas at Austin · Google/YouTube · University of Colorado Boulder
Parallel Decoding Distillation for Fast Image and Video Generation
Jul 28, 2026Neta Shaul, Chao Liu, Arash Vahdat +1Video Diffusion Models Diffusion Model Distillation
2Weizmann Institute of Science · 1NVIDIA
Beyond Facial Consistency: Personalized Person Image Generation with Holistic Identity Preservation
Jul 28, 2026Yuxuan Xiao, Shanshan Zhang, Jian Yang +1Subject-Driven Image Generation Identity-Preserving Image Generation
MorphUNet: Alpha-Controlled Biometric Transport for Diffusion-Based Face Morphing Attacks
Jul 27, 2026Taimoor Rizwan, Sara Atito, Zhenhua Feng +2Biometric Identification Diffusion-Based Image Generation
University of Surrey Guildford, United Kingdom · Jiangnan University Wuxi, China
Diff-ID: Identity Consistent Facial Image Generation and Morphing via Diffusion Models
Jul 27, 2026Taimoor Rizwan, Sara Atito, Muhammad Awais +2Image Generation Identity-Preserving Image Generation
Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey Guildford, United Kingdom · School of Artificial Intelligence and Computer Science Jiangnan University Wuxi, China
OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models
Jul 26, 2026Zhaoyuan He, Muhammad Muaz, Lili QiuVideo Diffusion Models Diffusion Transformer
Department of Computer Science, The University of Texas at Austin, Austin, TX, USA
PriSAR: 3D Geometric-Prior-Guided Diffusion for Parameter-Controlled SAR Image Generation
Jul 25, 2026Fan Zhang, Xuanting Wu, Fei Ma +2Diffusion Model Guidance Diffusion-Based Image Generation
College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China · 2Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
InnoText: A Unified Model for Visual Text Generation and Editing
Jul 24, 2026Haowei Liu, Runze He, Jian Lu +10Diffusion Transformer Diffusion-Based Image Generation
Shenzhen Campus of Sun Yat-Sen University · University of Chinese Academy of Sciences · Chongqing University of Post and Telecommunications +5
Inference-Time Scaling of Diffusion Models via Progressive Seed Pruning
Jul 23, 2026Rogerio Guimaraes, Pietro PeronaDiffusion Model Sampling Diffusion Sampling
California Institute of Technology, Pasadena CA 91125, USA
WearWow: Native 2K Multi-Garment Virtual Try-On via Adaptive Token Packing and Preference Alignment
Jul 22, 2026Xujie Zhang, Runyan Du, Song Chang +7Virtual Try-On Diffusion-Based Image Generation
Shenzhen Campus of Sun Yat-sen University, China · Meitu Lab, China
Analytic Distribution of Classifier-Free Guidance for Schedule Design
Jul 22, 2026Enze Jiang, Zheng MaClassifier-Free Guidance Diffusion Sampling
School of Mathematical Sciences Shanghai Jiao Tong University Shanghai, China
Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches
Jul 21, 2026Rick Wilming, Irem Ozseker, Luca Matteo Cornils +4Diffusion-Based Image Generation Medical Image Synthesis
Physikalisch-Technische Bundesanstalt Berlin, Germany · Technische Universität Berlin, Germany
DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer
Jul 20, 2026Yunpeng Bai, Yossi Gandelsman, Michaël GharbiDiffusion Transformer Pixel-Space Diffusion Models
The University of Texas at Austin · Reve
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Jul 20, 2026Shigui Li, Delu ZengDiffusion Model Alignment Diffusion Sampling
School of Mathematics, South China University of Technology, Guangzhou, China · School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China
Pixel-Space Diffusion Transformers
Jul 20, 2026Renye Yan, Jikang Cheng, You Wu +8Diffusion Transformer Pixel-Space Diffusion Models
Peking University, China · Nanjing University, China · Stanford University, USA +3
Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection
Jul 17, 2026Sodtavilan Odonchimed, Tsogt Enkhbayar, Oyunzul Munkhtamga +1Diffusion-Based Image Generation Physics-Based Simulation
The University of Tokyo · Mongolian University of Science and Technology · United Arab Emirates University
VQ-Touch: A Data-Efficient Tactile Generation Framework Across Sensors and Scenarios
Jul 16, 2026Kailin Lyu, Long Xiao, Jianing Zeng +3Tactile Sensing Vector-Quantized Variational Autoencoder
Institute of Automation, Chinese Academy of Sciences

Aug 5, 2026, stat.MLJ/K move · Enter open · S save

Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds

Yizhu Wang, Mu Niu, Xiaochen Yang

School of Mathematics and Statistics, University of Glasgow, Glasgow, U.K.

Latent Diffusion Models Generative Modeling Diffusion-Based Image Generation Score-Based Generative Modeling Diffusion Models

Open paper AskPDF arXiv

We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds. While diffusion models (DMs) have achieved state-of-the-art results in high-dimensional data synthesis, they rely on large training datasets and ignore intrinsic geometric structure. Latent diffusion models (LDMs) address the high dimensionality by learning a latent space, but they typically impose a Euclidean structure, failing to capture the underlying manifold geometry, especially problematic in data-sparse regimes. ILDM addresses these limitations by interpreting the latent space as a chart of an unknown Riemannian manifold, with geometry and uncertainty quantified through a probabilistic decoder. The forward process is a hybrid diffusion that switches between Riemannian and Euclidean dynamics based on local uncertainty, where the Riemannian component is governed by a probabilistic metric tensor derived from the decoder. To learn the generative dynamics, we introduce an approximate denoising score matching method tailored to the hybrid diffusion setting, enabling a backward process defined by hybrid Langevin dynamics. Experiments on COIL-100, MNIST, and cardiac MRI datasets demonstrate that ILDM significantly improves generation quality, achieving lower FID and LPIPS scores compared to standard diffusion and latent diffusion models.

Momentum

Related topics

Latest papers 189