Temporal Consistency in Video Generation

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 275% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 224

May 24, 2026cs.CV

DeltaCam: Differential Intrinsic Camera Modeling for Video Generation

Incorporating camera intrinsics into video generation models offers a principled way to control not only scene dynamics but also the imaging process that governs visual appearance. Prior work has primarily focused on extrinsic control, such as camera pose and motion, while treating intrinsic camera parameters as implicit or fixed. A key bottleneck is the lack of large-scale video datasets with accurate and diverse temporally varying camera metadata, which makes learning absolute camera parameterizations difficult. As a result, current models struggle to incorporate photographic camera behavior, including depth-of-field transitions, exposure variations, lens distortions, and color processing, in a controllable and temporally consistent manner. We introduce DeltaCam, a video diffusion framework that models camera behavior through

Δ

-parameterized neural camera adaptors, operating on relative changes in camera motion and intrinsics instead of absolute states. By learning this differential formulation from synthetic video data, we mitigate reliance on precise real-world camera labels and enable smooth, consistent control over imaging factors such as focal length, aperture, ISO, color temperature, and lens distortion. We extend this framework to real-world footage through two mechanisms: finetuning the controls on real image-metadata pairs for precise shot matching, and extracting disentangled embeddings for implicit video-to-video style transfer without requiring explicit camera parameters. By effectively separating scene content from intrinsic imaging behavior, DeltaCam enables camera-consistent video generation and editing operations that are difficult to achieve with existing models. Ultimately, our results establish a practical and scalable approach for bridging synthetic control and real-world photographic emulation.

Debabrata Mandal, Zhihan Peng, Yujie Wang +1

UNC, Chapel Hill, USA

Camera-Conditioned Video Generation Video Diffusion Models Controllable Video Generation Temporal Consistency in Video Generation

May 23, 2026cs.CV

DexSIM: Real-time Dexterous Simulation with Unified Causal Video Diffusion

Recent progress of video diffusion models have enabled extensive simulation of the physical world. While simulation with hand object interaction has been less explored. We propose DexSIM, a dexterous simulation framework for simulating dexterous manipulation in real-time. While previous works utilizing video diffusion and 3D reconstruction focus on navigation, dexterous manipulation has been limited while it has extensive applications for creating interactive experiences with the simulated world and for generating synthetic data for robotics. Existing methods lack real-time interactivity and long-term spatial consistency and memory. We propose a 2-stage training framework for DexSIM. First we train a bi-directional video diffusion model by jointly embedding the hand action trajectory and video in a unified feature space. We utilize gaussian heatmap hand encoding for more accurate hand representation. Then we conduct a roll-out based autoregressive training with updated spatial cache as attention sink for spatial memory, which improves long-term consistency and 3D aware dexterous manipulation simulation. DexSIM outperforms the baseline on pixel and semantic similarity, motion fidelity, and hand projection accuracy. It also allows new applications such as hand motion transfer and runs at 15.24 FPS real-time interactivity.

Adam Lee

UC Berkeley

Video Diffusion Models Real-Time Interactive Video Generation Robotics Simulation Video Generation Robotic Manipulation Temporal Consistency in Video Generation

May 22, 2026cs.CV

EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation

Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory. However, full-frame storage entangles persistent entity information with transient scene context, leading to irrelevant information leakage and high computational cost. We propose an entity-centric memory in the form of an entity-indexed bank of latent patches. We introduce sparse token conditioning compatible with pretrained models, restricting self-attention to entity-relevant tokens and reducing computational cost. To support this, we introduce a structured multi-shot script format. We additionally propose a budgeted memory update strategy to maintain a compact, evolving memory. Finally, we equip the entity representation with a noise-injection mechanism that enables fine-grained appearance control, preventing leakage of irrelevant information. Our method improves prompt adherence and efficiency while preserving subject consistency.

Jente Vandersanden, Matheus Gadelha, Chun-Hao P. Huang +2

Max Planck Institute for Informatics, Germany and Adobe Research, UK · Adobe Research, UK · Adobe Research, USA

Memory-Augmented Video Generation Identity-Preserving Video Generation Autoregressive Video Generation Multi-Shot Video Generation Temporal Consistency in Video Generation

May 22, 2026cs.CV

SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion

Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or resource-intensive retraining, restricting their flexibility and generalization. To bridge this gap, we present \textit{SimInsert}, a training-free paradigm that efficiently decouples the task into intuitive single-frame editing and semantic motion description. By harnessing the robust generative priors of image-to-video diffusion models, SimInsert propagates edits temporally, strictly preserving background invariance while enabling plausible, text-driven interactions between the inserted object and the dynamic environment. Our approach hinges on non-invasive guidance mechanisms that enforce structural consistency, facilitate seamless boundary fusion, and counteract the fidelity drift that typically accumulates during the denoising trajectory. Extensive quantitative experiments validate our efficacy: SimInsert surpasses state-of-the-art methods with an 18.8% gain in PSNR, 20.1% in SSIM, and a 44.1% decrease in LPIPS, offering a streamlined solution for high-fidelity video editing.

Xinyu Chen, Yuyi Qian, Jiang Lin +9

1State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Intelligence Science and Technology, Nanjing University, Suzhou, China · 4Xi’an Jiaotong-Liverpool University +3

Video Diffusion Models Video Editing Temporal Consistency in Video Generation

May 21, 2026cs.CV

WorldKV: Efficient World Memory with World Retrieval and Compression

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full KV-cache attention preserves this consistency but breaks real-time constraints: memory footprint and attention cost grow linearly with rollout length. Sliding window inference restores throughput but discards long-term consistency. We propose WorldKV, a training-free framework with two components: World Retrieval and World Compression. World Retrieval stores evicted KV-cache chunks in GPU/CPU memory and selectively retrieves scene-relevant chunks via camera/ action correspondence, inserting them back into the native attention window without re-encoding. World Compression prunes redundant tokens within each chunk via key-key similarity to an anchor frame, halving per-chunk storage to fit 2x more history under a fixed budget. On Matrix-Game-2.0 and LingBot- World-Fast, WorldKV matches or exceeds full-KV memory fidelity at roughly 2x the throughput, and is competitive with memory-trained baselines without any fine-tuning. Project Page: https://cvlab-kaist.github.io/WorldKV/

Jung Yi, Minjae Kim, Paul Hyunbin Cho +3

1KAIST AI · 2Naver AI Lab

KV Caching Memory-Augmented Video Generation Action-Conditioned World Models Efficient Inference for World Action Models Diffusion Model Caching KV-Cache Compression+3

May 21, 2026cs.CV

Cell Phantom Video Generation in Elliptical Fourier Descriptor Domain

Training Deep Neural Networks for tracking individual cells in biomedical videos requires a large amount of annotated data. The annotation of videos for cell tracking is very time consuming and often requires domain expertise; this explains the limited availability of public annotated data to address important medical problems like tissue repair or cancer treatment. Generating synthetic videos along with their Ground Truth annotations is a promising solution that relies, as a foundational first step, on the synthesis of single cell annotations (or phantoms). Phantoms need to be time consistent, as they have to replicate biological processes that are specific to the cell types. In this work, we propose a novel framework for generating videos of cell phantoms in the Elliptical Fourier Descriptors (EFDs) domain, a compact and geometrically interpretable representation for 2D closed contours. We represent the cell phantom evolution as a multivariate time series of EFD coefficients, introducing a strong prior for cell morphology and enabling the efficient generation of sequences that evolve coherently in time. Our experimental validation proves that modelling the temporal evolution in EFD space enables the generation of biologically plausible phantom videos. Our method can be used in generative pipelines for synthesizing annotated data for cell tracking, thus strongly mitigating the annotation effort for creating new datasets. Our code is available for download here: https://github.com/FrancescoBenedetto99/efd-cell-video-gen.

Francesco Benedetto, Roberto Basla, Luca Magri +1

Department of Electronics Information and Bioengineering, Politecnico di Milano, Italy

Synthetic Data Generation Video Generation Temporal Consistency in Video Generation

May 20, 2026cs.CV

BodyReLux: Temporally Consistent Full-Body Video Relighting

Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances in a temporally consistent way. Our model is trained on a hybrid dataset of pixel-aligned video relighting pairs, covering a diverse combination of lighting conditions, performances and viewpoints. To acquire such dataset, we combine traditional static One-Light-at-a-Time (OLAT) capture and a novel dynamic performance capture in which two smoothly varying lighting sequences are rapidly interleaved. Because the lighting operates above the human flicker-fusion threshold, the interleaving does not appear to strobe. We train our video relighting model from a pretrained text-to-video model to fully leverage the generative priors for producing high quality videos. To achieve accurate lighting control, we introduce a new lighting conditioning method that represents each light source as a token. We further condition on sequences of lighting using masked attention to support dynamic lighting control. Together with a carefully designed data augmentation pipeline, we achieve photorealistic, robust, and temporally consistent video relighting of subject-specific human performances.

Li Ma, Mingming He, Xueming Yu +4

Eyeline Labs, United States of America · Eyeline Labs, Canada · Eyeline Labs +2

Video Diffusion Models Controllable Video Generation Temporal Consistency in Video Generation

May 20, 2026cs.CV

GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation

Video world models can generate realistic futures from a single instruction, but they often fail to track the same physical points consistently across time. As a result, the generated videos appear plausible, yet lack the physical grounding required for reliable action execution, such as robot manipulation. We present GEM-4D, a geometry-grounded video world model that resolves this limitation by injecting dense 4D correspondence supervision distilled from a pretrained geometry foundation model into the video generative backbone during training. This supervision enables the model to jointly capture appearance and geometric structure while retaining a single-stream architecture with no additional inference cost. We further introduce an inverse dynamics module that converts correspondence-consistent video rollouts into executable robot trajectories, enabling direct deployment in both real-world and simulated manipulation. GEM-4D achieves state-of-the-art performance on both video prediction and geometric consistency across both simulation and realistic scenarios and improves real-world manipulation success from 61% to 81%. Additional results are available at https://gem-4d.github.io/.

Kaichen Zhou, Yuzhen Chen, Fangneng Zhan +8

Harvard AI and Robotics Lab, Harvard University · Media Lab and EECS, MIT · MIT-IBM Watson AI Lab +1

Physical Consistency in Video Generation Robot Motion Generation Video Generation Robotic Manipulation Temporal Consistency in Video Generation Video World Models

May 20, 2026cs.CV

FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching

Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free approaches fall into two categories: extensions of bidirectional models, which are tightly coupled to specific architectures and suffer from quality degradation over long horizons, and autoregressive models, which accumulate drift errors due to exposure bias and tend to produce repetitive motion patterns. To address these issues, we propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training. Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via \emph{Tweedie matching} to enforce both \textbf{manifold constraint and temporal consistency} across overlap regions. \emph{Stochastic early-phase sampling} then synchronizes per-window trajectories by injecting fresh noise after each Tweedie matching correction in the high-noise phase, before transitioning to deterministic ODE sampling to preserve fine-grained visual fidelity. Applied to various video generation models, our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any fine-tuning.

Jangho Park, Geon Yeong Park, Gihyun Kwon +1

1KAIST · 2Amazon

Video Diffusion Models Long Video Generation Temporal Consistency in Video Generation

May 19, 2026cs.CV

PhyWorld: Physics-Faithful World Model for Video Generation

World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse and realistic visual futures. However, using them as world simulators requires physically faithful video continuations, namely, generated videos that preserve the physical state implied by the conditioning input, and evolve in ways consistent with basic physical principles. We propose PhyWorld, a video generation world model designed to produce temporally coherent and physically faithful scene continuations through two-stage post-training. In the first stage, we improve video-to-video continuation with flow matching fine-tuning, encouraging stable visual attributes and coherent motion dynamics across frames. In the second stage, we align generated dynamics with physical principles using Direct Preference Optimization (DPO) over physics preference pairs, guiding the model toward outputs with higher physical plausibility. To evaluate PhyWorld, we use both standard video-quality benchmarks and a dedicated physical-faithfulness benchmark with per-law scoring. Experiments show that PhyWorld improves video consistency, achieving an average score of 0.769 on VBench compared with 0.756 or below for state-of-the-art baselines. PhyWorld also improves physical plausibility, reaching an average score of 3.09 on our physical-faithfulness benchmark compared with 2.99 for the strongest baseline. These results suggest that post-training large video generation models with continuation and physics-preference signals can make them more effective world simulators for Physical AI.

Pu Zhao, Juyi Lin, Timothy Rupprecht +10

Northeastern University · University of Georgia · Tulane University +1

Physics-Informed Generative Modeling Physical Consistency in Video Generation Video Generation Temporal Consistency in Video Generation Video World Models

May 18, 2026cs.CV

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos with constant memory consumption. However, the mismatch between training and inference, coupled with the challenge of maintaining long-term consistency, limits the effective utilization of foundation models. To mitigate these concerns, we propose \textbf{MIGA}, a novel infinite-frame long video generation method. Firstly, we propose an effective two-stage alignment mechanism that mitigates the training-inference gap by reducing the excessive noise span fed to the model. We then introduce an innovative dual consistency enhancement mechanism, where the self-reflection approach corrects early high-noise frames and the long-range frame guidance approach leverages later low-noise frames with broad coverage to steer generation, jointly improving temporal consistency. Extensive experiments on VBench and NarrLV demonstrate the state-of-the-art performance of MIGA. Our project page is available at https://xiaokunfeng.github.io/miga_homepage/.

X. Feng, J. Zhu, M. Wu +6

School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · AMAP, Alibaba Group, Beijing, China.

Video Diffusion Models Long Video Generation Video Generation Autoregressive Video Generation Temporal Consistency in Video Generation

May 18, 2026cs.CV

Temporal Aware Pruning for Efficient Diffusion-based Video Generation

Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token pruning has proven effective for ViTs and VLMs. However, most prior pruning methods are attention-based and operate per frame, failing to ensure the vital temporal coherence across frames in video generation tasks. In practice, naively adopting attention-only pruning causes noticeable degradation due to worsened background consistency, flickering, and reduced image quality. To address this, we propose TAPE, a training-free Temporal Aware Pruning for Efficient diffusion-based video generation. TAPE (i) applies temporal smoothing to align token-importance across adjacent frames and suppress selection jitter; and (ii) performs token reselection in selected layers to align token pruning with layers' diverse semantic focus and avoid error accumulation in specific areas; it also (iii) adopt a timestep-level budget scheduling that prunes aggressively at early noisy steps and relaxes pruning during fidelity-critical refinement. The experimental results show that TAPE delivers significant speedups while preserving high visual fidelity, outperforming prior token reduction approaches.

Sheng Li, Yang Sui, Junhao Ran +3

University of Pittsburgh · Rice University · Rutgers University +1

Video Diffusion Models Token Pruning Visual Token Pruning Diffusion Model Inference Acceleration Temporal Consistency in Video Generation

May 17, 2026cs.CV

HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos

Video outpainting generates plausible visual content beyond the original spatial extent of a video, playing a key role in adapting videos to diverse display formats. To support such use cases, it must enable large spatial extrapolation over long sequences. However, most existing methods address only one of these challenges or lack explicit mechanisms for ensuring global spatio-temporal consistency, leading to notable limitations. In this paper, we propose HL-OutPaint, a high-resolution video outpainting framework for long sequences. Our approach follows a coarse-to-fine strategy with a two-stage pipeline. We first construct Global Coarse Guidance (GCG), a low-resolution representation that captures global structure and dominant motion across the video. Unlike naive downsampling, GCG is built via a novel global-local frame swapping mechanism that couples sparse global keyframes with local temporal windows and exchanges information during sampling. This enables GCG to encode both long-term structural consistency and short-term temporal dynamics in a unified representation. Guided by this representation, HL-OutPaint then performs high-resolution outpainting to generate spatially detailed and temporally consistent content. By separating global structure modeling from fine-grained synthesis, our framework achieves stable, coherent generation for large spatial expansion and long video sequences. Extensive experiments show that HL-OutPaint outperforms existing methods in challenging scenarios involving wide spatial extrapolation and long video sequences.

Jeongeun Park, Janghyeok Han, Geonung Kim +4

POSTECH, Republic of Korea · Visual Display Business, Samsung Electronics, Republic of Korea

Long Video Generation Video Generation Temporal Consistency in Video Generation

May 17, 2026cs.CV

Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration

We study series-level cinematic remaking, a long-horizon video-to-video generation problem that localizes full episodes or films via stylization or actor replacement while strictly preserving narrative structure, motion choreography, and character identity across hundreds of shots. Existing video generation and editing pipelines often break down in this regime due to compounding identity drift, background mutation, and semantic erosion under large camera motions and viewpoint changes. We propose Soap2Soap, a multi-agent framework that enforces long-term language-visual consistency through a Dual-Bridge Consistency mechanism: a scene-aware JSON screenplay serving as a persistent semantic backbone, and dynamically allocated visual reference anchors at both scene and shot levels. To suppress drift before video synthesis, we introduce batch keyframe consistency, jointly generating multiple keyframes in a shared latent context via a grid-based formulation. A closed-loop verification agent further audits identity, stability, and alignment to trigger selective regeneration. Experiments on SoapBench demonstrate strong improvements over commercial video generation APIs in long-term consistency and narrative fidelity.

Yiren Song, Huilin Zhong, Kevin Qinghong Lin +2

Show Lab, National University of Singapore · University of Oxford · Lovart AI

Video-Reference Video Generation Long-Horizon Video Generation Agentic Video Generation Identity-Preserving Video Generation Video Editing Video Generation+2

May 17, 2026cs.CV

VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers

Video style transfer aims to render videos in a target artistic style while preserving content, structure, and motion. While image stylization has advanced rapidly, video stylization remains challenging due to temporal inconsistency. Most existing methods stylize frames or keyframes and enforce consistency via heuristic temporal propagation, which is brittle under occlusions, disocclusions, and long-term motion, leading to drift and flickering artifacts. We argue that a fundamental bottleneck lies in the lack of large-scale triplet data and a principled training paradigm that jointly models and disentangles style, content, and motion.To address this, we introduce VISTA-1000, a synthetic dataset with 1,000 styles and motion-aligned triplets of style reference, clean video, and stylized video, and propose a diffusion-transformer-based in-context video style transfer framework with a lightweight style adapter for robust style extraction. Extensive experiments demonstrate SOTA performance in style fidelity, temporal consistency, and content preservation.

Yiren Song, Wangzi Yao, Haofan Wang +1

Show Lab, National University of Singapore · Institute of Automation, Chinese Academy of Sciences · Lovart AI

Video Diffusion Models Temporal Consistency in Video Generation

May 17, 2026cs.CV

Image-to-Video Diffusion: From Foundations to Open Frontiers

Diffusion-based \textit{image-to-video} (I2V) generation has become a central direction in generative models by turning a reference image, with optional conditions, into a temporally coherent video. Compared with broader video generation settings, this task places stricter demands on content consistency, identity preservation, and motion coherence. Although the literature grows rapidly, existing works mostly discuss I2V generation within broader topics and still lack a dedicated taxonomy together with a systematic analysis centered on this field. This work addresses that gap by treating diffusion I2V generation as a standalone subject. It first reviews the task formulation, model architectures, datasets, and evaluation metrics, and then organizes existing methods through a taxonomy based on architecture and training paradigm. It further distills four core designs, namely condition encoding, temporal modeling, noise prior design, and spatial-temporal upsampling, and discusses representative application scenarios together with major open challenges.

Xianlong Wang, Wenbo Pan, Shijia Zhou +6

Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China · School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China · School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, China +3

Image-to-Video Generation Video Diffusion Models Temporal Consistency in Video Generation

May 15, 2026cs.CV

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion

Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to key-value caching, which limits its scalability to long video horizons. Existing remedies (e.g., sparse attention and KV-cache compression) reduce per-step cost but still rely on a linearly growing cache or irreversibly discard past context, and thus fail to address linear memory growth and streaming context management. To address this scalability bottleneck, we propose ARL2 (Attend Locally, Remember Linearly), a hybrid attention module that replaces quadratic cross-frame attention with a fixed-size recurrent state. We decompose self-attention into two branches: an intra-frame softmax branch for spatial detail and local dependencies, and an inter-frame gated recurrent linear branch that maintains a fixed-size state for streaming context. Our key insight is that softmax attention captures fine-grained local interactions, while a recurrent state provides controllable long-range memory. This design achieves linear-time scaling with constant memory while improving temporal consistency over the full-softmax model. To prevent noisy intermediate states from corrupting memory, we update the recurrent state only after the denoised pass. To avoid within-frame information asymmetry, all tokens share the same pre-update state rather than sequential updates. To the best of our knowledge, this is the first work to convert a pretrained AR video diffusion model into a hybrid linear attention architecture, through an efficient two-stage training scheme for AR video. With 75% of layers replaced by hybrid linear attention, the model achieves up to 2.26 wall-clock speedup and 54% memory reduction, while maintaining comparable quality with improving temporal consistency.

Kunyang Li, Mubarak Shah, Yuzhang Shang

Institute of Artificial Intelligence, University of Central Florida

Memory-Augmented Neural Networks Video Diffusion Models Self-Attention Linear Attention Autoregressive Video Generation Diffusion Model Inference Acceleration+1

May 15, 2026cs.GR

Evaluating Design Video Generation: Metrics for Compositional Fidelity

Generative video models are increasingly used in design animation tasks, yet no standardized evaluation framework exists for this domain. Unlike natural video generation, design animation imposes structured constraints: specific components shall animate with prescribed motion types, directions, speed and timing, while non-animated regions must remain stable and layout structure must be preserved. This paper provides a fully automated evaluation framework organized across four dimensions: layout fidelity, motion correctness, temporal quality, and content fidelity. This eliminates the reliance on subjective human evaluation and establishes a common basis for benchmarking progress in the field. We release the code and dataset here: https://github.com/purvanshi/lica-bench.

Adrienne Deganutti, Dingning Cao, Jaejung Seol +2

Lica World, San Francisco, United States of America.

Temporal Consistency in Video Generation Video Generation Evaluation

May 15, 2026cs.CV

FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization

Human-centric video customization, particularly at the garment level, has shown significant commercial value. However, existing approaches cannot support low-latency and interactive garment control, which is crucial for applications such as e-commerce and content creation. This paper studies how to achieve interactive multi-garment video customization while preserving motion coherence using only single-garment video data. We present FashionChameleon, a real-time and interactive framework for human-garment customization in autoregressive video generation, where users can interactively switch garment during generation. FashionChameleon consists of three key techniques: (i) Instead of training on multi-garment video data, we train a Teacher Model with In-Context Learning on a single reference-garment pair. By retaining the image-to-video training paradigm while enforcing a mismatch between the reference and garment image, the model is encouraged to implicitly preserve coherence during single-garment switching. (ii) To achieve consistency and efficiency during generation, we introduce Streaming Distillation with In-Context Learning, which fine-tunes the model with in-context teacher forcing and improves extrapolation consistency via gradient-reweighted distribution matching distillation. (iii) To extend the model for interactive multi-garment video customization, we propose Training-Free KV Cache Rescheduling, which includes garment KV refresh, historical KV withdraw, and reference KV disentangle to achieve garment switching while preserving motion coherence. Our FashionChameleon uniquely supports interactive customization and consistent long-video extrapolation, while achieving real-time generation at 23.8 FPS on a single GPU, 30-180

\times

faster than existing baselines.

Quanjian Song, Yefeng Shen, Mengting Chen +5

Xiamen University · Alibaba Group

Virtual Try-On Streaming Video Generation Autoregressive Video Generation Controllable Video Generation Temporal Consistency in Video Generation

May 14, 2026cs.CV

PanoWorld: Geometry-Consistent Panoramic Video World Modeling

We present PanoWorld, a panoramic video world model that generates geometry-consistent 360

\degree

video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do not explicitly constrain the underlying 3D scene state, producing outputs that appear plausible yet exhibit inconsistent depth, broken correspondences, and implausible motion across the spherical surface. We address this gap by framing panoramic video generation as a geometry- and dynamics-consistent latent state modeling problem rather than pure visual synthesis. Building on a pre-trained perspective video world model, we introduce two lightweight regularizers: a depth consistency loss against pseudo ground-truth panoramic depth, and a trajectory consistency loss that supervises the 3D world-frame positions of tracked points across time. We further apply spherical-geometry-aware adaptation to the conditioning and positional encoding. We additionally introduce PanoGeo, a unified geometry-aware panoramic video dataset with consistent depth, trajectory, and prompt annotations across diverse real and synthetic sources, used for both training and stratified evaluation. Experiments show that PanoWorld improves geometric consistency over prior panoramic generation methods while maintaining competitive visual realism, establishing that panoramic video generation must be treated as a geometric modeling problem to support the holistic spatial understanding requirements of embodied AI applications. Code is available at https://github.com/ostadabbas/PanoWorld.

Le Jiang, Xiangyu Bai, Bishoy Galoaa +7

Northeastern University

Physical Consistency in Video Generation Video Generation Temporal Consistency in Video Generation Video World Models

May 14, 2026cs.CV

RefDecoder: Enhancing Visual Generation with Conditional Video Decoding

Video generation powers a vast array of downstream applications. However, while the de facto standard, i.e., latent diffusion models, typically employ heavily conditioned denoising networks, their decoders often remain unconditional. We observe that this architectural asymmetry leads to significant loss of detail and inconsistency relative to the input image. To address this, we argue that the decoder requires equal conditioning to preserve structural integrity. We introduce RefDecoder, a reference-conditioned video VAE decoder by injecting high-fidelity reference image signal directly into the decoding process via reference attention. Specifically, a lightweight image encoder maps the reference frame into the detail-rich high-dimensional tokens, which are co-processed with the denoised video latent tokens at each decoder up-sampling stage. We demonstrate consistent improvements across several distinct decoder backbones (e.g., Wan 2.1 and VideoVAE+), achieving up to +2.1dB PSNR over the unconditional baselines on the Inter4K, WebVid, and Large Motion reconstruction benchmarks. Notably, RefDecoder can be directly swapped into existing video generation systems without additional fine-tuning, and we report across-the-board improvements in subject consistency, background consistency, and overall quality scores on the VBench I2V benchmark. Beyond I2V, RefDecoder generalizes well to a wide range of visual generation tasks such as style transfer and video editing refinement.

Xiang Fan, Yuheng Wang, Bohan Fang +2

University of Washington · University of North Carolina at Chapel Hill

Image-to-Video Generation Conditional Variational Autoencoder Temporal Consistency in Video Generation

May 14, 2026cs.CV

EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration

We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character identity. Long-form animation remains challenging because highly dynamic human motion must be synthesized against relatively static environments, making chunk-based generation prone to accumulated drift: (i) low-level quality drift, such as progressive degradation of static backgrounds, and (ii) high-level semantic drift, such as inconsistent character identity and view-dependent attributes. To address this issue, EverAnimate restores drifted flow trajectories by anchoring generation to a persistent latent context memory, consisting of two complementary mechanisms. (i) Persistent Latent Propagation maintains a context memory across chunks to propagate identity and motion in latent space while mitigating temporal forgetting. (ii) Restorative Flow Matching introduces an implicit restoration objective during sampling through velocity adjustment, improving within-chunk fidelity. With only lightweight LoRA tuning, EverAnimate outperforms state-of-the-art long-animation methods in both short- and long-horizon settings: at 10 seconds, it improves PSNR/SSIM by 8%/7% and reduces LPIPS/FID by 22%/11%; at 90 seconds, the gains increase to 15%/15% and 32%/27%, respectively.

Wuyang Li, Yang Gao, Mariam Hassan +4

Flow Matching Long-Horizon Video Generation Memory-Augmented Video Generation Human Motion Generation Flow-Based Generative Modeling Temporal Consistency in Video Generation

May 14, 2026cs.CV

Video Reconstruction using Diffusion-based Image-to-Video Generation with Trajectory Guidance

This paper addresses the problem of reconstructing missing or dropped frames in top-down drone video of autonomous surface vehicles performing structured maritime manoeuvres. We propose a pipeline that converts raw GPS telemetry and a single reference frame into a trajectory-guided video sequence using a pre-trained image-to-video diffusion model, requiring no domain-specific fine-tuning. GPS coordinates from onboard telemetry logs are projected into image space via an equirectangular mapping, producing per-vessel motion cues that condition the SG-I2V diffusion model. The generated frames are evaluated against ground-truth video using perceptual, temporal and trajectory-based metrics, and benchmarked against optical flow extrapolation and RIFE interpolation baselines. SG-I2V produces the most naturally appearing frames among all methods (BRISQUE 25.52, closest to ground-truth 23.64), the most realistic motion magnitude (temporal smoothness 1.14 vs. ground truth 1.42), and the strongest GPS trajectory adherence (9.31px vs. 28.70px for ground-truth, the latter reflecting approximate temporal alignment between footage and GPS logs rather than generation error), demonstrating that trajectory-guided diffusion synthesis is a viable approach to maritime video reconstruction under challenging low-texture, small-object conditions.

Stelio Bompai, Ioannis Kontopoulos, Giannis Spiliopoulos +2

Department of Electrical and Computer Engineering, National Technical University of Athens, Greece · Department of Product and Systems Design Engineering, University of the Aegean, Syros, Greece

Image-to-Video Generation Video Diffusion Models Video Frame Interpolation Controllable Video Generation Temporal Consistency in Video Generation

May 14, 2026cs.CV

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles as local heads for detail refinement, anchor heads for structural stabilization, and memory heads for long-range context aggregation, yet existing methods treat them uniformly, leading to suboptimal KV cache allocation. We propose Head Forcing, a training-free framework that assigns each head type a tailored KV cache strategy: local and anchor heads retain only essential tokens, while memory heads employ a hierarchical memory system with dynamic episodic updates for long-range consistency. A head-wise RoPE re-encoding scheme further ensures positional encodings remain within the pretrained range. Without additional training, Head Forcing extends generation from 5 seconds to minute-level duration, supports multi-prompt interactive synthesis, and consistently outperforms existing baselines. Project Page: https://jiahaotian-sjtu.github.io/headforcing.github.io/.

Jiahao Tian, Yiwei Wang, Gang Yu +1

AGI Lab, Westlake University · University of California at Merced · StepFun

Diffusion Transformer Autoregressive Diffusion Self-Attention Long-Horizon Video Generation KV-Cache Management Autoregressive Video Generation+2

May 14, 2026cs.CV

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation

Interactive real-time autoregressive video generation is essential for applications such as content creation and world modeling, where visual content must adapt to dynamically evolving event conditions. A fundamental challenge lies in balancing reactivity and stability: models must respond promptly to new events while maintaining temporal coherence over long horizons. Existing approaches distill bidirectional models into autoregressive generators and further adapt them via streaming long tuning, yet often exhibit persistent drift after condition changes. We identify the cause as conditional bias, where the teacher may provide condition-aligned but trajectory-agnostic guidance, biasing generation toward locally valid yet globally inconsistent modes. Inspired by Trust Region Policy Optimization, we propose Delta Forcing, a simple yet effective framework that constrains unreliable teacher supervision within an adaptive trust region. Specifically, Delta Forcing estimates transition consistency from the latent delta between teacher and generator trajectories, and uses it to balance teacher supervision with a monotonic continuity objective. This suppress unreliable teacher-induced shifts while preserving responsiveness to new events. Extensive experiments demonstrate that Delta Forcing significantly improves consistency while maintaining event reactivity.

Yuheng Wu, Xiangbo Gao, Tianhao Chen +4

1KAIST · *Work done when intern at Visko · 3Texas A&M University +3

Real-Time Interactive Video Generation Streaming Video Generation Video Generation Trust-Region Optimization Autoregressive Video Generation Temporal Consistency in Video Generation

May 13, 2026cs.CV

TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion

Recent text-to-video diffusion transformers generate visually compelling frames, yet still struggle with temporal coherence, often producing flickering, drifting, or unstable motion. We show that these failures leave a clear imprint inside the model: incoherent videos consistently exhibit irregular, fragmented temporal diagonals in their intermediate self-attention maps, whereas stable motion corresponds to smooth, band-diagonal patterns. Building on this observation, we introduce TeDiO, a training-free, inference-time method that reinforces temporal consistency by regularizing these internal attention patterns. TeDiO estimates diagonal smoothness, identifies unstable regions, and performs lightweight latent updates that promote coherent frame-to-frame dynamics, without modifying model weights or using external motion supervision. Across multiple video diffusion models (e.g., Wan2.1, CogVideoX), TeDiO delivers markedly smoother motion while preserving per-frame visual quality, offering an efficient plug-and-play approach to improving dynamic realism in modern video generation systems.

Nurislam Tursynbek, Zhiqiang Lao, Heather Yu +2

UNC Chapel Hill1 · Futurewei Technologies Inc2 · UCSD3

Video Diffusion Models Diffusion Transformer Temporal Attention Diffusion Models for Motion Generation Temporal Consistency in Video Generation

May 13, 2026cs.CV

Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation

Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache strategies usually apply unified historical-frame retention, implicitly assuming homogeneous historical dependencies across attention heads. We revisit historical-frame attention and reveal three distinct head types: Anchor Heads require broad long-range context, Wave Heads exhibit periodic temporal dependencies, and Veil Heads focus on initial and adjacent frames. Based on this finding, we propose Pyramid Forcing, a head-aware pyramidal KVCache framework that identifies head types offline, assigns behavior-specific cache policies, and supports heterogeneous cache lengths via efficient ragged-cache attention. Experiments on Self Forcing and Causal Forcing show that Pyramid Forcing consistently improves long-horizon generation quality on VBench-Long, increasing the 60-second Self Forcing score from 77.87 to 81.21 while enhancing motion dynamics, visual fidelity, and semantic consistency. Project: https://if-lab-pku.github.io/Pyramid-Forcing/.

Jiayu Chen, Junbei Tang, Wenbiao Zhao +6

Peking University · South China University of Technology · Xinjiang University +2

Self-Attention Long-Horizon Video Generation KV-Cache Management Autoregressive Video Generation Temporal Consistency in Video Generation Attention Head Specialization

May 12, 2026cs.CV

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot boundaries. Existing autoregressive models often struggle in this setting. Trained primarily for short-horizon continuation, they treat long sequences as extended single shots, inevitably suffering from motion stagnation and semantic drift during long rollouts. To bridge this gap, we introduce CausalCine, an interactive autoregressive framework that transforms multi-shot video generation into an online directing process. CausalCine generates causally across shot changes, accepts dynamic prompts on the fly, and reuses context without regenerating previous shots. To achieve this, we first train a causal base model on native multi-shot sequences to learn complex shot transitions prior to acceleration. We then propose Content-Aware Memory Routing (CAMR), which dynamically retrieves historical KV entries according to attention-based relevance scores rather than temporal proximity, preserving cross-shot coherence under bounded active memory. Finally, we distill the causal base model into a few-step generator for real-time interactive generation. Extensive experiments demonstrate that CausalCine significantly outperforms autoregressive baselines and approaches the capability of bidirectional models while unlocking the streaming interactivity of causal generation. Demo available at https://yihao-meng.github.io/CausalCine/

Yihao Meng, Zichen Liu, Hao Ouyang +11

1HKUST · 2Ant Group · 3SJTU

Real-Time Interactive Video Generation Long-Horizon Video Generation Streaming Video Generation Video Generation Autoregressive Video Generation Multi-Shot Video Generation+1

May 12, 2026cs.CV

RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation

While modern diffusion models excel at generating diverse single images, extending this to sequential generation reveals a fundamental challenge: balancing narrative dynamism with multi-character coherence. Existing methods often falter at this trade-off, leading to artifacts where characters lose their identity or the story stagnates. To resolve this critical tension, we introduce RealDiffusion, a unified framework designed to reconcile robust coherence with narrative dynamism. Heat diffusion serves as a dissipative prior that averages neighboring features along the sequence and removes high-frequency noise within the subject region. This suppresses attribute drift and stabilizes identity across frames. A region-aware stochastic process then introduces small perturbations that explore nearby modes and prevent collapse so the story maintains pose change and scene evolution. We thus introduce a lightweight, training-free Physics-informed Attention mechanism that injects controllable physical priors into the self-attention layers during inference. By modeling feature evolution as a configurable physical system, our method regularizes spatio-temporal relationships without suppressing intentional, prompt-driven changes. Extensive experiments demonstrate that RealDiffusion achieves substantial gains in character coherence while preserving narrative dynamism, outperforming state-of-the-art approaches. Code is available at https://github.com/ShmilyQi-CN/RealDiffusion.

Qi Zhao, Jun Chen, Ivor Tsang +1

Xi’an Jiaotong University, China · Zhejiang Normal University, China · SGIT AI Lab, State Grid Corporation of China +1

Diffusion-Based Image Generation Temporal Consistency in Video Generation

May 11, 2026cs.CV

Improving Human Image Animation via Semantic Representation Alignment

The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image animation works address these issues by incorporating human-specific semantic representations, e.g., dense poses or ID embeddings, as additional conditions. However, conditioning on these representations could decrease the generation flexibility. Moreover, their reliance on RGB pixel supervision also lacks emphasis on learning necessary 3D geometric relationships and temporal coherence. In contrast, we introduce a novel approach named SemanticREPA that leverages these semantic representations as supervision signals through representation alignment. Specifically, we begin by training a structure alignment module that aligns the structure representations obtained from video latents with video depth estimation features. We then fix the pretrained module, and utilize it to provide additional supervision on the structure representations of the diffusion models, achieving structure rectification to generate coherent and stable human structures. Simultaneously, we develop an ID alignment module to align the ID representations of the generated videos to face recognition features. We further propose to use the predicted structure representations to refine identity restoration in relevant regions. With structure and ID alignment, our method demonstrates superior quality on extended character motions and enhanced character consistency.

Chang Liu, Mengting Chen, Yixuan Huang +5

School of Artificial Intelligence, Shanghai Jiao Tong University, China · Alibaba Group, China

Image-to-Video Generation Video Diffusion Models Human Avatar Animation Video Generation Representation Alignment Temporal Consistency in Video Generation