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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune BEDLAM-CLIFF on VOccl3D | BEDLAM-CLIFF · VOccl3D test (Hard-Occlusion) | MPJPE (mm): 154.86 -> 136.34 | Improved |
| fine-tune BEDLAM-CLIFF on VOccl3D | BEDLAM-CLIFF · VOccl3D test (Low-Occlusion) | MPJPE (mm): 74.95 -> 69.46 | Improved |
| fine-tune CLIFF on VOccl3D | CLIFF · OcclType2-3DPW | MPJPE (mm): 99.49 -> 93.74 | Improved |
| fine-tune CLIFF on VOccl3D | CLIFF · OcclType1-3DPW | MPJPE (mm): 98.15 -> 95.17 | Improved |
| fine-tune CLIFF on VOccl3D | CLIFF · 3DPW | MPJPE (mm): 73.9 -> 71.10 | Improved |
| fine-tune CLIFF on VOccl3D | CLIFF · OCMotion | MPJPE (mm): 64.15 -> 64.29 | No clear effect |
| fine-tune CLIFF on VOccl3D | CLIFF · OCMotion | PA-MPJPE (mm): 40.16 -> 39.64 | Improved |
| use VOccl3D-B-CLIFF pseudo-labels instead of BEDLAM-CLIFF for STRIDE | STRIDE · VOccl3D test (Hard-Occlusion) | MPJPE (mm): 155.64 -> 136.43 | Improved |
| fine-tune YOLO11 on VOccl3D and COCO | YOLO11 · 3DPW | mAP50: 58.99 -> 59.89 | Improved |
| fine-tune YOLO11 on VOccl3D and COCO | YOLO11 · OCMotion | mAP50: 98.84 -> 99.10 | Improved |
| use VOccl3D-YOLO11 boxes instead of YOLO11 boxes (ablation) | VOccl3D-CLIFF · 3DPW | MPJPE (mm): 116.52 -> 114.85 | Improved |
| use ground-truth boxes instead of YOLO11 boxes (ablation) | VOccl3D-CLIFF · 3DPW | MPJPE (mm): 116.52 -> 71.10 | Improved |
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.
- CLIFF — CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation (ECCV 2022) · better on 10 of 10 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
- Occlusion-Aware Networks for 3D Human Pose Estimation in Video (ICCV 2019 · similarity 0.90)
- Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms (NeurIPS 2022 · similarity 0.90)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.88)
- $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.88)
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (CVPR 2024 · similarity 0.88)
- TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · similarity 0.86)
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.
