Research map / 3D vision / Face and shape
Ray-Distance Volume Rendering for Neural Scene Reconstruction
Ruihong Yin, Yunlu Chen, Sezer Karaoglu, Theo Gevers
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 |
|---|---|---|---|
| model volume density with ray-specific SRDF instead of SDF (ablation) | MonoSDF (MLP) · ScanNet | F-score: 0.733 -> 0.745 | Improved |
| add SRDF-SDF consistency loss (ablation) | SRDF-density MonoSDF (MLP) · ScanNet | F-score: 0.745 -> 0.776 | Improved |
| add self-supervised visibility task (ablation) | SRDF-density + consistency loss · ScanNet | F-score: 0.776 -> 0.794 | Improved |
| build visibility labels from both SRDF and SDF instead of one (ablation) | visibility task · ScanNet | F-score: 0.789 / 0.788 -> 0.794 | Improved |
| derive SRDF from SDF rather than a separate SRDF branch (ablation) | RS-Recon · ScanNet | F-score: 0.745 -> 0.628 | Hurt |
| drop the SDF branch and extract mesh from SRDF via TSDF fusion (ablation) | RS-Recon · ScanNet | F-score: 0.745 -> 0.568 | Hurt |
| apply SRDF solution to NeuS-based NeuRIS | NeuRIS · ScanNet | F-score: 0.692 -> 0.742 | Improved |
| use SRDF density for rendering | MonoSDF Grid · ScanNet / Replica / T&T | PSNR: 28.96 -> 30.09 (ScanNet) | Improved |
| use SRDF method vs MonoSDF on accuracy metric | ScanNet MLP · ScanNet | Acc: 0.035 -> 0.040 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HelixSurf — HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Volume Rendering of Neural Implicit Surfaces (NeurIPS 2021 · similarity 0.91)
- Learning Scene-Level Signed Directional Distance Function With Ellipsoidal Priors and Neural Residuals (TPAMI 2026 · similarity 0.89)
- Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions (AAAI 2025 · similarity 0.88)
- NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation (CVPR 2024 · similarity 0.88)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.87)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · 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.
