Research map / 3D vision / Human pose estimation
BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera
Tao Yu, Kaiwen Guo, Feng Xu, Yuan Dong, Zhaoqi Su, Jianhui Zhao, Jianguo Li, 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 the binding term between skeleton and graph-node deformation (ablation) | BodyFusion · occluded human sequences | skeleton tracking and fusion quality (qualitative) | Improved |
| add non-rigid registration terms to skeleton-only tracking (ablation) | BodyFusion · human sequences | fusion and tracking quality (qualitative) | Improved |
| jointly optimize the skeleton instead of using Kinect SDK skeletons as input (ablation) | BodyFusion · occluded human sequences | surface reconstruction quality (qualitative) | Improved |
| add the motion criterion to the attachment calculation (ablation) | BodyFusion attachments · loose-clothing arm | node-bone assignment (qualitative) | Improved |
| use attachment-based smoothness term instead of DynamicFusion's smoothness (ablation) | BodyFusion · arm tracking | deformation artifacts (qualitative) | Improved |
| replace DynamicFusion with BodyFusion | single-depth-camera fusion · Vicon-marker sequence | average error (cm): 4.4 cm -> 2.2 cm | Improved |
| replace VolumeDeform with BodyFusion | single-depth-camera fusion · Vicon-marker sequence | average error (cm): 3.7 cm -> 2.2 cm | Improved |
Later papers that compared with this method
1 later accepted paper reports BodyFusion as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor (CVPR 2018 · better on 2 of 2 shared results)
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.
- VolumeDeform — VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction (ECCV 2016) · 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
- DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor (CVPR 2018 · similarity 0.92)
- ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera (ECCV 2018 · similarity 0.90)
- HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs (ECCV 2018 · similarity 0.90)
- A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals (CVPR 2024 · similarity 0.85)
- SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering (CVPR 2024 · similarity 0.84)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · 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.
