Research map / 3D vision / Face and shape
Neural Deformation Graphs for Globally-Consistent Non-Rigid Reconstruction
Aljaz Bozic, Pablo Palafox, Michael Zollhofer, Justus Thies, Angela Dai, Matthias Niessner
Check 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 affinity consistency and sparsity losses (ablation) | Neural Deformation Graph (GRAPH) · DeformingThings4D synthetic sequences | Chamfer (× 10^-4): 0.50 -> 0.46 | Improved |
| Add affinity consistency and sparsity losses (ablation) | Neural Deformation Graph (GRAPH) · DeformingThings4D synthetic sequences | EPE3D (× 10^-2): 8.93 -> 8.03 | Improved |
| Add viewpoint consistency (ablation) | Neural Deformation Graph with affinity optimization · DeformingThings4D synthetic sequences | Chamfer (× 10^-4): 0.46 -> 0.44 | Improved |
| Add viewpoint consistency (ablation) | Neural Deformation Graph with affinity optimization · DeformingThings4D synthetic sequences | EPE3D (× 10^-2): 8.03 -> 4.12 | Improved |
| Add surface consistency (ablation) | Neural Deformation Graph with affinity optimization and viewpoint consistency · DeformingThings4D synthetic sequences | Chamfer (× 10^-4): 0.44 -> 0.40 | Improved |
| Add surface consistency (ablation) | Neural Deformation Graph with affinity optimization and viewpoint consistency · DeformingThings4D synthetic sequences | EPE3D (× 10^-2): 4.12 -> 1.16 | Improved |
| Add pose conditioning to local surface MLPs (ablation) | Neural Deformation Graph · DeformingThings4D synthetic sequences | Chamfer (× 10^-4): 0.46 -> 0.40 | Improved |
| Use Neural Deformation Graph instead of SIF | DeformingThings4D synthetic sequences · DeformingThings4D synthetic sequences | Chamfer (× 10^-4): 1.12 -> 0.40 | Improved |
| Use Neural Deformation Graph instead of Multiview DynamicFusion | DeformingThings4D synthetic sequences · DeformingThings4D synthetic sequences | EPE3D (× 10^-2): 3.06 -> 1.16 | Improved |
Closest papers by meaning
- Neural Non-Rigid Tracking (NeurIPS 2020 · similarity 0.90)
- Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints (ECCV 2020 · similarity 0.89)
- Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking (CVPR 2024 · similarity 0.89)
- Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction (CVPR 2024 · similarity 0.87)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.87)
- Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses (NeurIPS 2024 · similarity 0.86)
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.
