Research map / 3D vision / Depth and stereo
VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction
Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger
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 sparse SIFT color feature alignment term to dense depth alignment (ablation) | VolumeDeform · Scenes lacking geometric features, tangential motion | reconstruction/tracking quality | Improved |
| use depth-only tracking instead of combined depth and color (ablation) | VolumeDeform · Fig. 10 grid resolution study | drift | Hurt |
| use high-resolution deformation grid instead of low-resolution (ablation) | VolumeDeform · Fig. 10 grid resolution study | fine-scale deformation quality | Improved |
| increase input speed by skipping frames from 1x to beyond 3x (ablation) | VolumeDeform · Sunflower, every nth frame | tracking stability: stable up to 3x, fails above | Hurt |
| template-free reconstruction versus template-based Li et al. | VolumeDeform · Li et al. sequence | geometric error: average error 1mm | No clear effect |
| replace DynamicFusion coarse warp field and depth-only tracking with dense grid and SIFT | VolumeDeform · DynamicFusion scenes | canonical pose quality | Improved |
| compare to real-time template-tracking Zollhofer et al. | VolumeDeform · Zollhofer et al. sequence | reconstruction quality | No clear effect |
Later papers that compared with this method
4 later accepted papers report VolumeDeform as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- OcclusionFusion: Occlusion-Aware Motion Estimation for Real-Time Dynamic 3D Reconstruction (CVPR 2022 · better on 2 of 2 shared results)
- Neural Non-Rigid Tracking (NeurIPS 2020 · better on 2 of 2 shared results)
- KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences (CVPR 2017 · better on 2 of 2 shared results)
- 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
- Real-Time Enhancement of Dynamic Depth Videos with Non-Rigid Deformations (TPAMI 2016 · similarity 0.89)
- KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences (CVPR 2017 · similarity 0.88)
- Function4D: Real-Time Human Volumetric Capture From Very Sparse Consumer RGBD Sensors (CVPR 2021 · similarity 0.87)
- SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion (CVPR 2018 · similarity 0.87)
- MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video (CVPR 2024 · similarity 0.86)
- 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians (CVPR 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.
