Research map / 3D vision / Human pose estimation
HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUs
Zerong Zheng, Tao Yu, Hao Li, Kaiwen Guo, Qionghai Dai, Lu Fang, 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 IMU term to non-rigid depth tracking (HybridFusion vs DoubleFusion) | DoubleFusion · Vicon comparison sequence | avg of max error (m): 0.0854 -> 0.0655 | Improved |
| use hybrid depth+IMU tracking instead of Helten et al. hybrid tracker | Helten et al. [11] · Helten dataset D1 | joint tracking error (mm): 35.7 -> 20.9 | Improved |
| use hybrid depth+IMU tracking instead of Helten et al. hybrid tracker | Helten et al. [11] · Helten dataset D5 | joint tracking error (mm): 59.1 -> 43.5 | Improved |
| add per-frame sensor calibration optimization (ablation) | HybridFusion · simple sequence (qualitative) | tracking and fusion quality | Improved |
| add adaptive confidence-based TSDF fusion (ablation) | HybridFusion · far distance, occlusion, fast motion (qualitative) | surface fusion detail | Improved |
| add IMUs to handle severe occlusion in loop closure | HybridFusion · turning-around motions (qualitative) | loop closure completeness | Improved |
| use 8 IMUs instead of full 17 IMUs (ablation) | HybridFusion · leapfrogging, punching motions | avg joint position error | No clear effect |
Later papers that compared with this method
1 later accepted paper reports HybridFusion as a baseline in their results tables; 0 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 0 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.
- DoubleFusion — DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor (CVPR 2018) · better on 1 of 1 shared result
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 0.90)
- DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor (CVPR 2018 · similarity 0.89)
- DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion (CVPR 2024 · similarity 0.84)
- UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Units (CVPR 2025 · similarity 0.83)
- I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions (CVPR 2024 · similarity 0.82)
- HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations (CVPR 2024 · similarity 0.82)
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.
