Research map / 3D vision / Face and shape
DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor
Tao Yu, Zerong Zheng, Kaiwen Guo, Jianhui Zhao, Qionghai Dai, Hao Li, Gerard Pons-Moll, 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 |
|---|---|---|---|
| Use DoubleFusion's double-layer representation and joint motion tracking instead of BodyFusion | Human performance tracking · Vicon dataset, sequence szq | Maximum Error (m): 0.0554 -> 0.0458 | Improved |
| Use DoubleFusion's double-layer representation and joint motion tracking instead of BodyFusion | Human performance tracking · Vicon dataset, sequence szq | Average Error (m): 0.0277 -> 0.0221 | Improved |
| Replace the double node graph with a uniformly sampled free-form node graph (ablation) | DoubleFusion · Dynamic human surface reconstruction | surface reconstruction quality | Hurt |
| Remove far-body nodes and use only the on-body node graph (ablation) | DoubleFusion · Dynamic human surface reconstruction with loose clothing | surface completeness | Hurt |
| Use only body-shape correspondences and omit non-rigid registration (ablation) | DoubleFusion joint motion tracking · Qualitative joint motion tracking evaluation | surface reconstruction quality | Hurt |
| Use body-shape and fused-surface correspondences but omit non-rigid registration (ablation) | DoubleFusion joint motion tracking · Qualitative joint motion tracking evaluation | surface reconstruction quality | Hurt |
| Use fused-surface correspondences only, removing body-shape correspondences (ablation) | DoubleFusion joint motion tracking · Qualitative on-body correspondence evaluation | tracking robustness | Hurt |
| Add volumetric shape-pose optimization (ablation) | DoubleFusion · Public 4D sequence rendered as a single-view depth sequence | per-frame tracking error | Improved |
Later papers that compared with this method
3 later accepted papers report DoubleFusion as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- RobustFusion: Robust Volumetric Performance Reconstruction Under Human-Object Interactions From Monocular RGBD Stream (TPAMI 2022 · better on 3 of 3 shared results)
- Robust 3D Self-Portraits in Seconds (CVPR 2020 · better on 3 of 3 shared results)
- HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs (ECCV 2018 · better on 1 of 1 shared result)
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.
- BodyFusion — BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera (ICCV 2017) · 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
- BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera (ICCV 2017 · similarity 0.92)
- HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs (ECCV 2018 · similarity 0.89)
- ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera (ECCV 2018 · similarity 0.87)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.85)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.84)
- SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering (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.
