Research map / 3D vision / NeRF and radiance fields
NeRF-Texture: Synthesizing Neural Radiance Field Textures
Yi-Hua Huang, Yan‐Pei Cao, Yu‐Kun Lai, Ying Shan, Lin Gao
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 NeRF-Texture's coarse-fine texture representation instead of a synthesized 2D image texture | NeRF-Texture · Captured textures, SIFID | SIFID: 1.05 -> 0.60 | Improved |
| use neural texture instead of 2D texture at 80 degree elevation | NeRF-Texture · Captured textures, elevation 80 degrees | SIFID: 1.75 -> 0.82 | Improved |
| disentangle meso-structure from base shape versus Instant-NGP on DTU Scan 55 | NeRF-Texture · DTU Scan 55 | PSNR: 34.108 -> 32.378 | Hurt |
| disentangle meso-structure from base shape versus Instant-NGP on DTU Scan 83 | NeRF-Texture · DTU Scan 83 | PSNR: 42.602 -> 43.842 | Improved |
| add latent clustering constraint (ablation) | NeRF-Texture · texture synthesis | synthesis artifacts (qualitative) | Improved |
| raise patch resolution from 128x128 to 256x256 (ablation) | NeRF-Texture · texture reconstruction | quality and storage | No clear effect |
| increase training views from 4 to 64 (ablation) | NeRF-Texture · rock ground scene | render quality (qualitative) | Improved |
| add explicit base shape projection and KNN/ray tracing versus Instant-NGP | NeRF-Texture · Rendering speed 512x512 | FPS: 307.05 -> 84.45 | Hurt |
Later papers that compared with this method
1 later accepted paper reports NeRF-Texture as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- 3D Gaussian Texture for Real-time Mesoscale Appearance Synthesis and Rendering (ECCV 2026 · better on 8 of 8 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 Radiance Fields From Sparse RGB-D Images for High-Quality View Synthesis (TPAMI 2022 · similarity 0.90)
- NeRFLight: Fast and Light Neural Radiance Fields Using a Shared Feature Grid (CVPR 2023 · similarity 0.90)
- NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation (CVPR 2024 · similarity 0.89)
- A General Implicit Framework for Fast NeRF Composition and Rendering (AAAI 2024 · similarity 0.88)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.88)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.88)
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.
