Research map / 3D vision / 3D generation
DCHM: Depth-Consistent Human Modeling for Multiview Detection
Jiahao Ma, Tianyu Wang, Miaomiao Liu, David Ahmedt-Aristizabal, Chuong Nguyen
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 |
|---|---|---|---|
| replace Depth Anything v2 depth with DCHM fine-tuned depth reconstruction | label-free localization · Wildtrack | MODA: 68.7 -> 84.2 | Improved |
| replace Depth Anything v2 depth with DCHM fine-tuned depth reconstruction | label-free localization · Wildtrack | MODP: 55.1 -> 80.3 | Improved |
| replace Depth Pro with DCHM reconstruction | label-free localization · Wildtrack | MODA: 72.8 -> 84.2 | Improved |
| use DCHM instead of UMPD | label-free detection · MultiviewX | MODA: 67.5 -> 78.4 | Improved |
| use DCHM instead of UMPD | label-free detection · Wildtrack | MODA: 76.6 -> 84.2 | Improved |
| use DCHM instead of UMPD | label-free detection · Wildtrack | Recall: 86.0 -> 84.6 | Hurt |
| use DCHM instead of UMPD | label-free detection · MultiviewX | Precision: 93.4 -> 90.7 | Hurt |
| add DCHM human modeling to MvCHM supervised localization | supervised multiview detection · Wildtrack | MODA: 95.3 -> 95.5 | Improved |
| add DCHM human modeling to MvCHM supervised localization | supervised multiview detection · Wildtrack | MODP: 84.5 -> 90.2 | Improved |
| add multiview detection compensation to YOLOv9/YOLOv11 (ablation) | monocular pedestrian detectors · Wildtrack+ | AP | Improved |
| add iterative training loops (up to three) (ablation) | DCHM · Wildtrack | MODA | Improved |
| use superpixel-wise supervision instead of pixel-wise (ablation) | DCHM Gaussian splatting · Wildtrack | MODA | 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.
- Depth Pro — Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025) · better on 2 of 2 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
- MV2GF: Multi-view Pedestrian Detection with a Visual Geometric Foundation Model (ECCV 2026 · similarity 0.86)
- Human Detection and Segmentation via Multi-View Consensus (ICCV 2021 · similarity 0.86)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.85)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.84)
- MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention (CVPR 2025 · similarity 0.84)
- HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes (CVPR 2024 · similarity 0.84)
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.
