Skip to content

Author

Kaitong Cai

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

DreamHand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery

DreamHand is introduced, an offline clip-level framework that extracts features via a Deterministic Clean-Latent Encoder and decodes them with a Bidirectional Spatiotemporal Decoder, offering a scalable path from everyday human video to robot manipulation data.

Yufei Liu, Xixi Wang, Hao Li et al. · 0 citations