AI Paper Atlas

Research map / 3D vision / Human pose estimation

VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions

Yash Garg, Saketh Bachu, Arindam Dutta, Rohit Lal, Sarosij Bose, Calvin-Khang Ta, M. Salman Asif, Amit Roy-Chowdhury

ICCV 2025 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune BEDLAM-CLIFF on VOccl3DBEDLAM-CLIFF · VOccl3D test (Hard-Occlusion)MPJPE (mm): 154.86 -> 136.34Improved
fine-tune BEDLAM-CLIFF on VOccl3DBEDLAM-CLIFF · VOccl3D test (Low-Occlusion)MPJPE (mm): 74.95 -> 69.46Improved
fine-tune CLIFF on VOccl3DCLIFF · OcclType2-3DPWMPJPE (mm): 99.49 -> 93.74Improved
fine-tune CLIFF on VOccl3DCLIFF · OcclType1-3DPWMPJPE (mm): 98.15 -> 95.17Improved
fine-tune CLIFF on VOccl3DCLIFF · 3DPWMPJPE (mm): 73.9 -> 71.10Improved
fine-tune CLIFF on VOccl3DCLIFF · OCMotionMPJPE (mm): 64.15 -> 64.29No clear effect
fine-tune CLIFF on VOccl3DCLIFF · OCMotionPA-MPJPE (mm): 40.16 -> 39.64Improved
use VOccl3D-B-CLIFF pseudo-labels instead of BEDLAM-CLIFF for STRIDESTRIDE · VOccl3D test (Hard-Occlusion)MPJPE (mm): 155.64 -> 136.43Improved
fine-tune YOLO11 on VOccl3D and COCOYOLO11 · 3DPWmAP50: 58.99 -> 59.89Improved
fine-tune YOLO11 on VOccl3D and COCOYOLO11 · OCMotionmAP50: 98.84 -> 99.10Improved
use VOccl3D-YOLO11 boxes instead of YOLO11 boxes (ablation)VOccl3D-CLIFF · 3DPWMPJPE (mm): 116.52 -> 114.85Improved
use ground-truth boxes instead of YOLO11 boxes (ablation)VOccl3D-CLIFF · 3DPWMPJPE (mm): 116.52 -> 71.10Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy