3 papers
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.CV2025
RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters
Xiaolin Liu, Tianyi Zhou, Hongbo Kang +6
Crowd evacuation simulation is critical for enhancing public safety, and demanded for realistic virtual environments. Current mainstream evacuation models overlook the complex huma…
cs.CV2025
RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Image
Jing Huang, Hao Wen, Tianyi Zhou +3
This paper focuses on spatially consistent hundreds of human pose and shape reconstruction from a single large-scene image with various human scales under arbitrary camera FoVs (Fi…