4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction
Presents novel computer vision architecture for 4D reconstruction that advances interaction modeling beyond optimization-based approaches.
AI Summary
Researchers introduce 4D-HOF, a feed-forward framework using conditional flow matching to reconstruct 4D hand-object interactions from foundation model estimates with state-of-the-art accuracy.
Excerpt
Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize interactions from random noise, which can lead to unstable interaction prediction. We introduce 4D-HOF, a feed-forward framework that reconstructs 4D hand-object interactions from coarse but informative estimates produced by vision foundation models. Concretely, we learn a conditional flow matching model that transports foundation-model-derived hand-