← Search

Ziming Sun

2 accepted papers

2025

Instance-Level Video Depth in Groups Beyond Occlusions

ICCV 2025poster

Depth estimation in dynamic, multi-object scenes remains a major challenge, especially under severe occlusions. Existing monocular models, including foundation models, struggle with instance-wise depth consistency due to their reliance on global regression. We tackle this problem from two key aspect…

Cited by 0SourcePDFScholar
2024

RePOSE: 3D Human Pose Estimation via Spatio-Temporal Depth Relational Consistency

ECCV 2024poster

"We introduce RePOSE, a simple yet effective approach for addressing occlusion challenges in the learning of 3D human pose estimation (HPE) from videos. Conventional approaches typically employ absolute depth signals as supervision, which are adept at discernible keypoints but become less reliable w…