AI RESEARCH
FastVMT: Eliminating Redundancy in Video Motion Transfer
arXiv CS.CV
•
ArXi:2602.05551v2 Announce Type: replace 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.