Research map / 3D vision / Depth and stereo
ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera
Chao Li, Zheheng Zhao, Xiaohu Guo
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 distance-transform correspondences for silhouette vertices (ablation) | two-level registration · tangential motion tracking | tracking convergence | Improved |
| add node graph segmentation and two-level optimization on top of DT-based DynamicFusion | DynamicFusion with DT · fast inter-frame motion parallel to screen | reconstruction quality | Improved |
| use too few fixed clusters (k less than needed, e.g. 2) (ablation) | ArticulatedFusion · dancing/arm motion | reconstruction quality | Hurt |
| use a moderate fixed cluster count (30) or dynamic clustering (ablation) | ArticulatedFusion · arm motion | reconstruction quality | Improved |
| use as many clusters as nodes (ablation) | ArticulatedFusion · arm motion | reconstruction quality | Hurt |
| reject TSDF integration when voxels collide after warping | depth fusion · dynamic scenes | surface correctness | Improved |
| compare against BodyFusion with skeleton prior | ArticulatedFusion · Vicon marker error | max marker error | No clear effect |
| use ArticulatedFusion instead of VolumeDeform on 5x speed input | dynamic reconstruction · sunflower sequence skipping 5 frames | reconstruction success | Improved |
| use segmentation instead of pre-scanned template (Tzionas and Gall) | ArticulatedFusion · donkey hand puppet | error distribution | Improved |
Closest papers by meaning
- BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera (ICCV 2017 · similarity 0.90)
- Real-Time Enhancement of Dynamic Depth Videos with Non-Rigid Deformations (TPAMI 2016 · similarity 0.89)
- DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor (CVPR 2018 · similarity 0.87)
- VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction (ECCV 2016 · similarity 0.87)
- Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera (NeurIPS 2022 · similarity 0.86)
- ReMatching Dynamic Reconstruction Flow (ICLR 2025 · 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.
