3 papers
cs.CV2026
PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimation
Zhuoyang Xie, Yibo Zhao, Hui Huang +2
Monocular 3D human pose estimation remains a fundamentally ill-posed inverse problem due to the inherent depth ambiguity in 2D-to-3D lifting. While contemporary video-based methods…
cs.GR2025
ArcPro: Architectural Programs for Structured 3D Abstraction of Sparse Points
Qirui Huang, Runze Zhang, Kangjun Liu +3
We introduce ArcPro, a novel learning framework built on architectural programs to recover structured 3D abstractions from highly sparse and low-quality point clouds. Specifically,…
cs.CV2024
CRAYM: Neural Field Optimization via Camera RAY Matching
Liqiang Lin, Wenpeng Wu, Chi-Wing Fu +2
We introduce camera ray matching (CRAYM) into the joint optimization of camera poses and neural fields from multi-view images. The optimized field, referred to as a feature volume,…