Research map / Point clouds / Shape and surface completion
Geodesic-HOF: 3D Reconstruction Without Cutting Corners
Ziyun Wang, Eric A. Mitchell, Volkan Isler, Daniel D. Lee
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 |
|---|---|---|---|
| use learned geodesic neighborhoods instead of Euclidean neighborhoods for normal estimation (ablation) | Geodesic-HOF · ShapeNet test, mean | Normal consistency: 0.818 -> 0.828 | Improved |
| use learned geodesic neighborhoods instead of Euclidean neighborhoods for normal estimation (ablation) | Geodesic-HOF · ShapeNet test categories | Normal consistency | Mixed |
| use Geodesic-HOF point reconstruction rather than AtlasNet | ShapeNet test, mean · ShapeNet test | Chamfer distance: 0.175 -> 0.141 | Improved |
Closest papers by meaning
- GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation (ICCV 2023 · similarity 0.89)
- DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting (ECCV 2024 · similarity 0.88)
- From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data (ICML 2026 · similarity 0.88)
- Critical Regularizations for Neural Surface Reconstruction in the Wild (CVPR 2022 · similarity 0.87)
- NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024 · similarity 0.87)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (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.
