Research map / 3D vision / Face and shape
DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras
Yang Zheng, Ruizhi Shao, Yuxiang Zhang, Tao Yu, Zerong Zheng, Qionghai Dai, Yebin Liu
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 |
|---|---|---|---|
| add attention module to PIFuHD (ablation) | PIFuHD · MultiHuman single human | point-to-surface distance: 0.914 -> 0.845 | Improved |
| add attention module to PIFu (ablation) | PIFu · MultiHuman two closely-interactive | point-to-surface distance: 1.745 -> 1.773 | No clear effect |
| add attention module to PIFu (ablation) | PIFu · MultiHuman single human | point-to-surface distance: 1.131 -> 1.054 | Improved |
| add multi-view self-attention fusion instead of mean pooling (ablation) | DeepMultiCap · MultiHuman three persons | point-to-surface distance: 1.309 -> 1.130 | Improved |
| add attention module instead of mean pooling (ablation) | DeepMultiCap · MultiHuman two natural-interactive | point-to-surface distance: 1.251 -> 1.041 | Improved |
| add SMPL global normal maps (ablation) | DeepMultiCap · MultiHuman two natural-interactive | point-to-surface distance: 1.277 -> 1.041 | Improved |
| add SMPL global normal maps (ablation) | DeepMultiCap · MultiHuman single human | point-to-surface distance: 1.063 -> 0.895 | Improved |
| add SMPL global normal maps (ablation) | DeepMultiCap · MultiHuman three persons | point-to-surface distance: 1.334 -> 1.130 | Improved |
| add SMPL proxy to PIFu-style multi-view fusion (PaMIR vs ours) | PaMIR · MultiHuman three persons | point-to-surface distance: 1.414 -> 1.130 | Improved |
| add temporal fusion (ablation) | DeepMultiCap · real-world image sequence | temporal consistency (qualitative) | Improved |
Closest papers by meaning
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.87)
- MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention (CVPR 2025 · similarity 0.85)
- PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling (CVPR 2024 · similarity 0.85)
- MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction (AAAI 2025 · similarity 0.85)
- GeoAvatar: Geometrically-Consistent Multi-Person Avatar Reconstruction from Sparse Multi-View Videos (CVPR 2025 · similarity 0.85)
- MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR 2024 · similarity 0.85)
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.
