Preprint
Aug 2026
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation
This work introduces CamChoreo, a benchmark of 4,229 real single-shot clips with expert-annotated temporal segments, and proposes CamDistill, which distills the same geometric knowledge into lightweight camera tokens during training and removes the 3D model at inference.
Da-Zhao Du, Shiyan Du, Jian Liu et al.
· 0 citations