3 papers
cs.CV2025
LONG3R: Long Sequence Streaming 3D Reconstruction
Zhuoguang Chen, Minghui Qin, Tianyuan Yuan +2
Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either re…
cs.CV2025
TrackOcc: Camera-based 4D Panoptic Occupancy Tracking
Zhuoguang Chen, Kenan Li, Xiuyu Yang +3
Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tr…
cs.CV2023
End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context
Yiran Guan, Zhuoguang Chen, Wenzheng Zeng +2
In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), to facilitate video gaze estimation via capturing spatial-temporal interaction context among head, face, and eye…