Research map / 3D vision / NeRF and radiance fields
CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
Yixing Lao, Xiaogang Xu, zhipeng cai, Xihui Liu, Hengshuang Zhao
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 correspondence priors (losses) to vanilla NeRF | NeRF · LLFF 3 views | PSNR: 16.79 -> 19.83 | Improved |
| add correspondence priors to vanilla NeRF | NeRF · LLFF 3 views | Depth MAE: 1.66 -> 0.91 | Improved |
| add correspondence priors to NeuS | NeuS · DTU 3 views | Chamfer-L1: 6.16 -> 2.63 | Improved |
| add correspondence priors to NeuS | NeuS · DTU 3 views (object) | PSNR: 16.06 -> 20.58 | Improved |
| add correspondence augmentation (flip, swap, scale, propagation) (ablation) | CorresNeRF · LLFF 3 views | PSNR: 18.50 -> 19.83 | Improved |
| add correspondence outlier filtering (ablation) | CorresNeRF · LLFF 3 views | PSNR: 19.32 -> 19.83 | Improved |
| add pixel reprojection loss (ablation) | CorresNeRF · LLFF 3 views | PSNR: 18.16 -> 19.83 | Improved |
| add correspondence depth loss (ablation) | CorresNeRF · LLFF 3 views | PSNR: 17.75 -> 19.83 | Improved |
| add correspondence depth loss (ablation) | CorresNeRF · LLFF 3 views | LPIPS: 0.51 -> 0.29 | Improved |
| add correspondence augmentation (ablation) | CorresNeRF · LLFF 3 views | Depth MAE: 1.15 -> 0.91 | Improved |
| increase Gaussian noise on correspondences from 0 to 4 px std (ablation) | CorresNeRF · LLFF 3 views | PSNR: 19.83 -> 18.31 | Hurt |
| increase noise std from 0 to 1 px (ablation) | CorresNeRF · LLFF 3 views | PSNR: 19.83 -> 19.31 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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
- UNISURF — UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction (ICCV 2021) · better on 2 of 2 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
- AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training (CVPR 2023 · similarity 0.91)
- Explicit Correspondence Matching for Generalizable Neural Radiance Fields (TPAMI 2025 · similarity 0.91)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.90)
- ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field (NeurIPS 2024 · similarity 0.90)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.90)
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.
