Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Crowd4D: Scene-Aware Monocular 4D Crowd Reconstruction
Hongbo Kang, Tianyi Zhou, Qingyang Yang +4
Recovering scene-consistent 4D crowd motion from monocular video in large-scale scenes remains challenging due to severe depth ambiguity and complex scene geometry. Existing monocu…
cs.CV2026
OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images
Yuanwang Yang, Hongliang Liu, Muxin Zhang +4
Monocular 3D human reconstruction in real-world scenarios remains highly challenging due to frequent occlusions from surrounding objects, people, or image truncation. Such occlusio…