Research map / 3D vision / Face and shape
Geometry Processing with Neural Fields
Guandao Yang, Serge Belongie, Bharath Hariharan, Vladlen Koltun
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 |
|---|---|---|---|
| initialize Langevin dynamics from rejection-sampled rough shape | neural field surface sampling · Dino | CDr: 1.54 -> 1.04 | Improved |
| initialize Langevin dynamics from rejection-sampled rough shape | neural field surface sampling · Armadillo | CDr: 1.36 -> 1.02 | Improved |
| initialize Langevin dynamics from rejection-sampled rough shape | neural field surface sampling · Dino | EMDr: 3.38 -> 1.15 | Improved |
| initialize Langevin dynamics from rejection-sampled rough shape | neural field surface sampling · Armadillo | EMDr: 3.30 -> 1.08 | Improved |
| initialize Langevin dynamics from rejection-sampled rough shape | neural field surface sampling · Dino | sampling time: 0.15 -> 0.21 | Hurt |
| initialize Langevin dynamics from rejection-sampled rough shape | neural field surface sampling · Armadillo | sampling time: 0.12 -> 0.18 | Hurt |
| replace invertible deformation network with SIREN (no inverse) (ablation) | neural field surface sampling · 2D rectangle SDF deformation | topology preservation (qualitative) | Hurt |
| remove positional encoding from deformation network (No PE) (ablation) | neural field surface sampling · 2D rectangle SDF deformation | deformation complexity (qualitative) | Hurt |
| optimize only stretching loss Ls instead of both losses (ablation) | neural field surface sampling · 2D rectangle SDF deformation | shape quality (qualitative) | Mixed |
| optimize only bending loss Lb instead of both losses (ablation) | neural field surface sampling · 2D rectangle SDF deformation | shape quality (qualitative) | Mixed |
| apply ARAP to marching-cubes mesh instead of neural field thin-shell optimization | neural field surface sampling · Cactus, Armadillo, Dino deformation | volume distortion (qualitative) | Hurt |
| remesh (simplify) extracted mesh before ARAP, or use SR-ARAP | neural field surface sampling · ARAP baselines | deformation quality (qualitative) | Improved |
Closest papers by meaning
- Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing (NeurIPS 2025 · similarity 0.89)
- Improving Neural Network Surface Processing with Principal Curvatures (NeurIPS 2024 · similarity 0.88)
- Neural Processing of Tri-Plane Hybrid Neural Fields (ICLR 2024 · similarity 0.85)
- Grounding Continuous Representations in Geometry: Equivariant Neural Fields (ICLR 2025 · similarity 0.85)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (CVPR 2024 · similarity 0.85)
- CoFie: Learning Compact Neural Surface Representations with Coordinate Fields (NeurIPS 2024 · 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.
