Research map / 3D vision / Face and shape
Neural Implicit Shape Editing using Boundary Sensitivity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| apply boundary sensitivity to optimize the prescribed deformation directly in the space of expressible deformations | Rigid editing · Bunny | Killing energy: 254 -> 320 | Hurt |
| apply boundary sensitivity to optimize the prescribed deformation directly in the space of expressible deformations | Rigid editing · Cactus | Killing energy: 11 -> 6 | Helped |
| add a volume constraint by projecting the parameter update onto the locally linear isochronic subspace | Mean-curvature-flow smoothing · Volume-preserving smoothing, 86 iterations | Volume decrease: 80% -> 1.6% | Helped |
| increase Tikhonov regularization from λ=10⁻¹ to λ=10¹ (ablation) | Semantic editing · Semantic editing | Similarity to source shape | Helped |
| increase Tikhonov regularization from λ=10⁻¹ to λ=10¹ (ablation) | Semantic editing · Semantic editing | Iterations to converge to a similar result: 860 compared to <10 | Hurt |
| split a large target deformation into equal parts and apply it iteratively (ablation) | Geometric editing · Large target deformations | Deformation recovery accuracy | Helped |
| prescribe displacement only on a local part of the surface and leave the remaining boundary unconstrained | Semantic editing · Plausible local edits | Semantic plausibility | Helped |
| prescribe semantically implausible local displacements | Semantic editing · Opposing wing displacements | Target adherence and meaningfulness | Hurt |
| use boundary sensitivity for semantic editing with a DualSDF generative network instead of prescribing edits through spherical primitives | DualSDF · ShapeNet semantic editing | Qualitative plausibility | No clear effect |
Closest papers by meaning
- Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing (NeurIPS 2025 · similarity 0.91)
- Implicit Neural Surface Deformation with Explicit Velocity Fields (ICLR 2025 · similarity 0.88)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.88)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (CVPR 2024 · similarity 0.88)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.87)
- 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.