FastVMT: Eliminating Redundancy in Video Motion Transfer

• URL: http://arxiv.org/abs/2602.05551v1
• Date: Thu, 05 Feb 2026 11:15:59 GMT
• Title: FastVMT: Eliminating Redundancy in Video Motion Transfer
• Authors: Yue Ma, Zhikai Wang, Tianhao Ren, Mingzhe Zheng, Hongyu Liu, Jiayi Guo, Mark Fong, Yuxuan Xue, Zixiang Zhao, Konrad Schindler, Qifeng Chen, Linfeng Zhang,
• Abstract summary: Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video.<n>Recent methods predominantly use the Diffusion Transformer (DiT) architecture.<n>FastVMT achieves a 3.43x speedup without degrading the visual fidelity or the temporal consistency of the generated videos.
• Score: 67.23955701588211
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video. Recent methods predominantly use the Diffusion Transformer (DiT) architecture. To achieve satisfactory runtime, several methods attempt to accelerate the computations in the DiT, but fail to address structural sources of inefficiency. In this work, we identify and remove two types of computational redundancy in earlier work: motion redundancy arises because the generic DiT architecture does not reflect the fact that frame-to-frame motion is small and smooth; gradient redundancy occurs if one ignores that gradients change slowly along the diffusion trajectory. To mitigate motion redundancy, we mask the corresponding attention layers to a local neighborhood such that interaction weights are not computed unnecessarily distant image regions. To exploit gradient redundancy, we design an optimization scheme that reuses gradients from previous diffusion steps and skips unwarranted gradient computations. On average, FastVMT achieves a 3.43x speedup without degrading the visual fidelity or the temporal consistency of the generated videos.

Related papers

• IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation [58.297199313494]
  Implicit methods capture motion semantics directly from driving video, but suffer from identity leakage and entanglement between motion and appearance.<n>We propose a novel implicit motion representation that compresses per-frame motion into compact 1D motion tokens.<n>Our methodology employs a three-stage training strategy to enhance the training efficiency and ensure high fidelity.
  arXiv  Detail & Related papers  (2026-02-07T11:17:20Z)
• BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching [6.354675628412448]
  Block-Wise Caching (BWCache) is a training-free method to accelerate DiT-based video generation.<n> experiments on several video diffusion models demonstrate that BWCache achieves up to 2.24$times$ speedup with comparable visual quality.
  arXiv  Detail & Related papers  (2025-09-17T07:58:36Z)
• AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration [45.62669899834342]
  Diffusion Transformers (DiTs) have proven effective in generating high-quality videos but are hindered by high computational costs.<n>We propose Asymmetric Reduction and Restoration (AsymRnR), a training-free and model-agnostic method to accelerate video DiTs.
  arXiv  Detail & Related papers  (2024-12-16T12:28:22Z)
• Spectral Motion Alignment for Video Motion Transfer using Diffusion Models [54.32923808964701]
  Spectral Motion Alignment (SMA) is a framework that refines and aligns motion vectors using Fourier and wavelet transforms.<n> SMA learns motion patterns by incorporating frequency-domain regularization, facilitating the learning of whole-frame global motion dynamics.<n>Extensive experiments demonstrate SMA's efficacy in improving motion transfer while maintaining computational efficiency and compatibility across various video customization frameworks.
  arXiv  Detail & Related papers  (2024-03-22T14:47:18Z)
• Motion-Aware Video Frame Interpolation [49.49668436390514]
  We introduce a Motion-Aware Video Frame Interpolation (MA-VFI) network, which directly estimates intermediate optical flow from consecutive frames. It not only extracts global semantic relationships and spatial details from input frames with different receptive fields, but also effectively reduces the required computational cost and complexity.
  arXiv  Detail & Related papers  (2024-02-05T11:00:14Z)
• Decouple Content and Motion for Conditional Image-to-Video Generation [6.634105805557556]
  conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i.e., one image and text. Previous cI2V generation methods conventionally perform in RGB pixel space, with limitations in modeling motion consistency and visual continuity. We propose a novel approach by disentangling the target RGB pixels into two distinct components: spatial content and temporal motions.
  arXiv  Detail & Related papers  (2023-11-24T06:08:27Z)
• Spatial-Temporal Transformer based Video Compression Framework [44.723459144708286]
  We propose a novel Spatial-Temporal Transformer based Video Compression (STT-VC) framework. It contains a Relaxed Deformable Transformer (RDT) with Uformer based offsets estimation for motion estimation and compensation, a Multi-Granularity Prediction (MGP) module based on multi-reference frames for prediction refinement, and a Spatial Feature Distribution prior based Transformer (SFD-T) for efficient temporal-spatial joint residual compression. Experimental results demonstrate that our method achieves the best result with 13.5% BD-Rate saving over VTM.
  arXiv  Detail & Related papers  (2023-09-21T09:23:13Z)
• Motion-inductive Self-supervised Object Discovery in Videos [99.35664705038728]
  We propose a model for processing consecutive RGB frames, and infer the optical flow between any pair of frames using a layered representation. We demonstrate superior performance over previous state-of-the-art methods on three public video segmentation datasets.
  arXiv  Detail & Related papers  (2022-10-01T08:38:28Z)
• Learning Comprehensive Motion Representation for Action Recognition [124.65403098534266]
  2D CNN-based methods are efficient but may yield redundant features due to applying the same 2D convolution kernel to each frame. Recent efforts attempt to capture motion information by establishing inter-frame connections while still suffering the limited temporal receptive field or high latency. We propose a Channel-wise Motion Enhancement (CME) module to adaptively emphasize the channels related to dynamic information with a channel-wise gate vector. We also propose a Spatial-wise Motion Enhancement (SME) module to focus on the regions with the critical target in motion, according to the point-to-point similarity between adjacent feature maps.
  arXiv  Detail & Related papers  (2021-03-23T03:06:26Z)

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.