Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model

About

We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even provided video) or their combinations. This is different from previous methods which only can work on a specific motion domain or show weak control abilities with diffusion prior. To achieve our goal, we design several domain-aware motion field adapters (\ie, MOFA-Adapters) to control the generated motions in the video generation pipeline. For MOFA-Adapters, we consider the temporal motion consistency of the video and generate the dense motion flow from the given sparse control conditions first, and then, the multi-scale features of the given image are wrapped as a guided feature for stable video diffusion generation. We naively train two motion adapters for the manual trajectories and the human landmarks individually since they both contain sparse information about the control. After training, the MOFA-Adapters in different domains can also work together for more controllable video generation. Project Page: https://myniuuu.github.io/MOFA_Video/

Muyao Niu, Xiaodong Cun, Xintao Wang, Yong Zhang, Ying Shan, Yinqiang Zheng• 2024

Related benchmarks

TaskDatasetResultRank
Image-to-Video GenerationCustom 27-video (test)
Motion Smoothness0.994
7
Video SynthesisCholec80 (test)
FVD651.1
7
Video GenerationOpenVid (test)
LPIPS0.3
7
Video SynthesisCataract-1k (test)
FVD722.2
7
Video SynthesisCATARACTS (test)
FVD713.4
7
Video GenerationWebVid (test)
LPIPS0.351
7
Object-level Motion ControlMC-Bench
Temporal Coherence25
6
Scene Graph AlignmentCataract-1k (test)
BB IoU45.6
5
Scene Graph AlignmentCATARACTS (test)
BB IoU42.5
5
Scene Graph AlignmentCholec80 (test)
BB IoU59.9
5
Showing 10 of 14 rows

Other info

Follow for update