Research map / 3D vision / Face and shape
Volume Rendering of Neural Implicit Surfaces
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 |
|---|---|---|---|
| model density as Laplace CDF of an SDF instead of a generic density | NeRF · DTU | Chamfer distance (mm): 1.89 -> 0.86 | Helped |
| use VolSDF without masks instead of IDR with masks | IDR · DTU | Chamfer distance (mm): 0.90 -> 0.86 | No clear effect |
| use VolSDF instead of NeRF | NeRF · DTU | PSNR: 30.65 -> 30.38 | No clear effect |
| use VolSDF instead of NeRF++ | NeRF++ · BlendedMVS | Chamfer l1: 51.8% mean improvement | Helped |
| use VolSDF instead of NeRF++ | NeRF++ · BlendedMVS | PSNR: 27.55 -> 27.08 | No clear effect |
| use error-bounded adaptive ray sampling instead of uniform or two-network hierarchical sampling (ablation) | VolSDF · DTU | Chamfer distance and PSNR | Helped |
| raise positional encoding level from 6 to 10 in VolSDF (ablation) | VolSDF · DTU Bunny | Chamfer distance | Mixed |
| add normal dependency to the radiance field (ablation) | VolSDF · BlendedMVS | geometry/radiance disentanglement | Helped |
Closest papers by meaning
- Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors (CVPR 2023 · similarity 0.93)
- NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies (CVPR 2023 · similarity 0.89)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.89)
- Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions (AAAI 2025 · similarity 0.88)
- NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction (NeurIPS 2024 · similarity 0.87)
- 2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images (CVPR 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.