FastVMT: Eliminating Redundancy in Video Motion Transfer

TL;DR

FastVMT enhances video motion transfer by removing computational redundancies, achieving over three times faster processing without sacrificing quality or consistency.

Contribution

The paper introduces novel techniques to eliminate motion and gradient redundancies in DiT-based video transfer, significantly improving speed.

Findings

FastVMT achieves a 3.43x speedup on average.

It maintains visual fidelity and temporal consistency.

Redundancy removal does not degrade output quality.

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.