3 papers
cs.CV2025
DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion
Jianbin Jiao, Xina Cheng, Kailun Yang +2
3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occ…
cs.CV2024
LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras
Fei Teng, Jiaming Zhang, Jiawei Liu +4
Leveraging rich information is crucial for dense prediction tasks. Light field (LF) cameras are instrumental in this regard, as they allow data to be sampled from various perspecti…
cs.CV2024
Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers
Jianbin Jiao, Xina Cheng, Weijie Chen +3
3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications t…