Research map / 3D vision / Face and shape
Neural Density-Distance Fields
Itsuki Ueda, Yoshihiro Fukuhara, Hirokatsu Kataoka, Hiroaki Aizawa, Hidehiko Shishido, Itaru Kitahara
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 NeDDF instead of NeuS for novel view synthesis | NeDDF · NeRF synthetic (mean) | PSNR: 25.93 -> 27.02 | Improved |
| use NeRF instead of NeDDF for novel view synthesis | NeDDF · NeRF synthetic (mean) | PSNR: 27.02 -> 31.01 | Hurt |
| add reprojection error as a preprocessing step (100 iterations) before photometric optimization (ablation) | camera pose localization · Lego, 200 test viewpoints with poor initial poses | camera pose recovery range | Improved |
| use reprojection error alone instead of combined with photometric error (ablation) | camera pose localization · Lego, 200 test viewpoints | camera pose error | No clear effect |
| add the auxiliary gradient axis (w) for cusp removal (ablation) | NeDDF · NeRF synthetic rendering (qualitative) | spurious density in empty regions | Improved |
| add reprojection error preprocessing on Materials scene (ablation) | camera pose localization · NeRF synthetic Materials | localization accuracy | Hurt |
| add reprojection error preprocessing on Mic and Ship scenes (ablation) | camera pose localization · NeRF synthetic Mic and Ship | localization accuracy | No clear effect |
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.
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 7 of 9 shared results
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
- Neural Unsigned Distance Fields for Implicit Function Learning (NeurIPS 2020 · similarity 0.88)
- Behind the Scenes: Density Fields for Single View Reconstruction (CVPR 2023 · similarity 0.86)
- RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency (NeurIPS 2023 · similarity 0.86)
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.85)
- How to Train Neural Field Representations: A Comprehensive Study and Benchmark (CVPR 2024 · similarity 0.85)
- ResFields: Residual Neural Fields for Spatiotemporal Signals (ICLR 2024 · similarity 0.84)
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.
