Research map / 3D vision / Face and shape
Coordinate Quantized Neural Implicit Representations for Multi-view Reconstruction
Sijia Jiang, Jing Hua, Zhizhong Han
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 |
|---|---|---|---|
| add quantized coordinates to UNISURF | UNISURF · DTU (15 scans) | mean Chamfer distance: 1.02 -> 0.80 | Improved |
| add quantized coordinates to NeuS | NeuS · DTU (15 scans) | mean Chamfer distance: 0.87 -> 0.73 | Improved |
| add quantized coordinates to Geo-NeuS | Geo-NeuS · DTU (15 scans) | mean Chamfer distance: 0.62 -> 0.60 | Improved |
| add quantized coordinates to MonoSDF | MonoSDF · Replica | F-score: 86.18 -> 90.16 | Improved |
| use a very high quantization resolution (R=51200) rather than low (1024) (ablation) | UNISURF with quantized coordinates · DTU subset | Chamfer distance: 1.67 -> 0.59 | Improved |
| increase resolution beyond optimum to 102400 (ablation) | UNISURF with quantized coordinates · DTU subset | Chamfer distance: 0.59 -> 0.69 | Hurt |
| replace nearest interpolation with trilinear interpolation (ablation) | UNISURF with quantized coordinates · DTU subset | Chamfer distance: 0.592 -> 0.72 | Hurt |
| use discrete coordinates together with their own positional encodings (not mixed with continuous) (ablation) | UNISURF with quantized coordinates · DTU subset | Chamfer distance: 0.75 -> 0.592 | Improved |
| extract meshes with discrete instead of continuous coordinates in marching cubes (ablation) | UNISURF with quantized coordinates · DTU subset | Chamfer distance: 0.592 -> 0.586 | No clear effect |
| add quantized coordinates to HF-NeuS with higher-frequency positional encoding | HF-NeuS · DTU (4 scans, higher-frequency PE) | mean Chamfer distance: 1.25 -> 1.05 | Improved |
| add quantized coordinates (runtime cost) | NeuS · DTU, 1000 iterations | runtime: 104.726 -> 104.591 | No clear effect |
| add quantized coordinates to NeuS on scan 83 | NeuS · DTU scan 83 | Chamfer distance: 1.01 -> 1.40 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 2 of 2 shared results
- Geo-NeuS — Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (NeurIPS 2022) · better on 1 of 1 shared result
- HF-NeuS — HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (NeurIPS 2022) · better on 1 of 1 shared result
- UNISURF — UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction (ICCV 2021) · 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
- Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D representations (NeurIPS 2022 · similarity 0.88)
- Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations (CVPR 2021 · similarity 0.88)
- CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture (ICLR 2022 · similarity 0.87)
- Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (NeurIPS 2022 · similarity 0.86)
- Improving Neural Implicit Surfaces Geometry With Patch Warping (CVPR 2022 · similarity 0.86)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · 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.
