Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification

About

Synthesizing realistic human-object interactions (HOI) in video is challenging due to the complex, instance-specific interaction dynamics of both humans and objects. Incorporating controllability in video generation further adds to the complexity. Existing controllable video generation approaches face a trade-off: sparse controls like keypoint trajectories are easy to specify but lack instance-awareness, while dense signals such as optical flow, depths or 3D meshes are informative but costly to obtain. We propose VHOI, a two-stage framework that first densifies sparse trajectories into HOI mask sequences, and then fine-tunes a video diffusion model conditioned on these dense masks. We introduce a novel HOI-aware motion representation that uses color encodings to distinguish not only human and object motion, but also body-part-specific dynamics. This design incorporates a human prior into the conditioning signal and strengthens the model's ability to understand and generate realistic HOI dynamics. Experiments demonstrate state-of-the-art results in controllable HOI video generation. VHOI is not limited to interaction-only scenarios and can also generate full human navigation leading up to object interactions in an end-to-end manner. Project page: https://vcai.mpi-inf.mpg.de/projects/vhoi/.

Wanyue Zhang, Lin Geng Foo, Thabo Beeler, Rishabh Dabral, Christian Theobalt• 2025

Related benchmarks

TaskDatasetResultRank
HOI Video GenerationHOIGen-1M 1.0 (test)
CLIPSIM0.305
14
HOI Video GenerationBEHAVE (test)
CLIPSIM0.3061
5
HOI Video Generationin-the-wild dataset (test)
Fréchet Video Distance (FVD)484
4
Showing 3 of 3 rows

Other info

Follow for update