Motion-Adaptive Temporal Attention for Lightweight Video Generation with Stable Diffusion

• URL: http://arxiv.org/abs/2603.17398v1
• Date: Wed, 18 Mar 2026 06:20:57 GMT
• Title: Motion-Adaptive Temporal Attention for Lightweight Video Generation with Stable Diffusion
• Abstract summary: We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models.<n>We inject lightweight temporal attention modules into all UNet transformer blocks via a cascaded strategy.<n>Our ablation studies reveal a clear trade-off between noise correlation and motion amplitude, providing a practical inference-time control for diverse generation behaviors.
• Score: 1.9349092719498848
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models. Rather than treating all video content uniformly, our method dynamically adjusts temporal attention receptive fields based on estimated motion content: high-motion sequences attend locally across frames to preserve rapidly changing details, while low-motion sequences attend globally to enforce scene consistency. We inject lightweight temporal attention modules into all UNet transformer blocks via a cascaded strategy -- global attention in down-sampling and middle blocks for semantic stabilization, motion-adaptive attention in up-sampling blocks for fine-grained refinement. Combined with temporally correlated noise initialization and motion-aware gating, the system adds only 25.8M trainable parameters (2.9\% of the base UNet) while achieving competitive results on WebVid validation when trained on 100K videos. We demonstrate that the standard denoising objective alone provides sufficient implicit temporal regularization, outperforming approaches that add explicit temporal consistency losses. Our ablation studies reveal a clear trade-off between noise correlation and motion amplitude, providing a practical inference-time control for diverse generation behaviors.

Related papers

• In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion [52.18702395026718]
  We introduce In-Context Forcing, a progressive autoregressive paradigm that utilizes contexts with decreasing noise levels.<n>By applying less masking to distant frames and more masking to adjacent ones, this approach provides adaptive guidance.<n>Our method significantly outperforms state-of-the-art approaches in both visual fidelity and inference speed.
  arXiv  Detail & Related papers  (2026-08-05T13:54:31Z)
• Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation [32.824608968455294]
  Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text.<n>We propose WInning Noise Retrieval and Optimization (WINRO), a framework that improves text-motion alignment by selecting and refining such tickets before diffusion sampling.<n>WINRO consistently improves text-motion fidelity across different base models, MDM and MotionLCM, on HumanML3D without retraining.
  arXiv  Detail & Related papers  (2026-07-07T22:32:10Z)
• RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling [51.279397568734424]
  Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis.<n>DiTs suffer from high inference latency and computational costs due to the quadratic complexity of 3D attention.<n>We introduce bftextRhymeFlow, a training-free framework that decouples the denoising trajectories of different frames.
  arXiv  Detail & Related papers  (2026-06-04T15:49:37Z)
• Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation [9.132288507881592]
  Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention.<n>We propose Precision-Allocated Sparse Attention (PASA), a training-free framework designed for highly efficient and temporally smooth video generation.
  arXiv  Detail & Related papers  (2026-04-14T02:51:52Z)
• Event-based Visual Deformation Measurement [76.25283405575108]
  Visual Deformation Measurement aims to recover dense deformation fields by tracking surface motion from camera observations.<n>Traditional image-based methods rely on minimal inter-frame motion to constrain the correspondence search space.<n>We propose an event-frame fusion framework that exploits events for temporally dense motion cues and frames for spatially dense precise estimation.
  arXiv  Detail & Related papers  (2026-02-16T01:04:48Z)
• Characterizing Motion Encoding in Video Diffusion Timesteps [50.13907856401258]
  We study how motion is encoded in video diffusion timesteps by the trade-off between appearance editing and motion preservation.<n>We identify an early, motion-dominant regime and a later, appearance-dominant regime, yielding an operational motion-appearance boundary in timestep space.
  arXiv  Detail & Related papers  (2025-12-18T21:20:54Z)
• Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models [11.913945404405865]
  Most video diffusion models (VDMs) generate videos in an autoregressive manner, generating subsequent iteration frames conditioned on previous ones.<n>We propose Adaptive Begin-of-Video Tokens (ada-BOV) for autoregressive VDMs.
  arXiv  Detail & Related papers  (2025-11-15T08:29:14Z)
• LiteAttention: A Temporal Sparse Attention for Diffusion Transformers [1.3471268811218626]
  LiteAttention exploits temporal coherence to enable evolutionary computation skips across the denoising sequence.<n>We implement a highly optimized LiteAttention kernel on top of FlashAttention and demonstrate substantial speedups on production video diffusion models.
  arXiv  Detail & Related papers  (2025-11-14T08:26:55Z)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• DiTVR: Zero-Shot Diffusion Transformer for Video Restoration [48.97196894658511]
  DiTVR is a zero shot video restoration framework that couples a diffusion transformer with trajectory aware attention and a flow consistent sampler.<n>Our attention mechanism aligns tokens along optical flow trajectories, with particular emphasis on vital layers that exhibit the highest sensitivity to temporal dynamics.<n>The flow guided sampler injects data consistency only into low-frequency bands, preserving high frequency priors while accelerating cache.
  arXiv  Detail & Related papers  (2025-08-11T09:54:45Z)
• DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization [2.0032531485183345]
  We introduce DiViD, the first end-to-end video diffusion framework for explicit static-dynamic factorization.<n>DiViD extracts a global static token from the first frame and per-frame dynamic tokens, explicitly removing static content from the motion code.<n>We evaluate DiViD on real-world benchmarks using swap-based accuracy and cross-leakage metrics.
  arXiv  Detail & Related papers  (2025-07-18T14:09:18Z)
• JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation [13.168628936598367]
  JointTuner is a framework that enables joint optimization of appearance and motion components.<n>AiT Loss disrupts the flow of appearance-related components, guiding the model to focus exclusively on motion learning.<n>JointTuner is compatible with both UNet-based models and Diffusion Transformer-based models.
  arXiv  Detail & Related papers  (2025-03-31T11:04:07Z)
• ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation [101.19290845597918]
  This paper presents a Motion Estimation (ME) module and an Event Denoising (ED) module jointly optimized in a mutually reinforced manner. Taking temporal correlation as guidance, ED module calculates the confidence that each event belongs to real activity events, and transmits it to ME module to update energy function of motion segmentation for noise suppression.
  arXiv  Detail & Related papers  (2022-03-22T13:40:26Z)
• Intrinsic Temporal Regularization for High-resolution Human Video Synthesis [59.54483950973432]
  temporal consistency is crucial for extending image processing pipelines to the video domain. We propose an effective intrinsic temporal regularization scheme, where an intrinsic confidence map is estimated via the frame generator to regulate motion estimation. We apply our intrinsic temporal regulation to single-image generator, leading to a powerful " INTERnet" capable of generating $512times512$ resolution human action videos.
  arXiv  Detail & Related papers  (2020-12-11T05:29:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.