Research map / 3D vision / NeRF and radiance fields
Dual-Camera All-in-Focus Neural Radiance Fields
Xianrui Luo, Zijin Wu, Juewen Peng, Huiqiang Sun, Zhiguo Cao, Guosheng Lin
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 optical flow warping to homography (ablation) | DC-NeRF · Book | PSNR: 21.15 -> 25.32 | Improved |
| add homography to optical flow warping (ablation) | DC-NeRF · Book | PSNR: 22.54 -> 25.32 | Improved |
| add optical flow warping to homography (ablation) | DC-NeRF · Plate | PSNR: 19.45 -> 24.05 | Improved |
| add defocus-aware fusion module (ablation) | DC-NeRF · Duck | PSNR: 22.43 -> 23.54 | Improved |
| add defocus-aware fusion module (ablation) | DC-NeRF · Bear | PSNR: 23.64 -> 25.12 | Improved |
| add confidence map (ablation) | DC-NeRF · Duck | PSNR: 21.50 -> 23.54 | Improved |
| add confidence map (ablation) | DC-NeRF · Bear | PSNR: 22.55 -> 25.12 | Improved |
| add L_focus loss (ablation) | DC-NeRF · Duck | PSNR: 23.37 -> 23.54 | Improved |
| add L_fusion loss (ablation) | DC-NeRF · Duck | PSNR: 22.54 -> 23.54 | Improved |
| add L_focus loss (ablation) | DC-NeRF · Bear | PSNR: 25.02 -> 25.12 | Improved |
| train separate NeRFs with fusion instead of single joint NeRF (ablation) | Ours-joint · Doll | PSNR: 21.11 -> 24.22 | Improved |
| feed unaligned or aligned ultra-wide images directly to baseline NeRF | Deblur-NeRF · Smartphone fg-focused | PSNR: 23.23 -> 21.04 | 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.
- Deblur-NeRF — Deblur-NeRF: Neural Radiance Fields From Blurry Images (CVPR 2022) · better on 5 of 6 shared results
- DP-NeRF — DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors (CVPR 2023) · better on 3 of 3 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
- Dynamic Neural Radiance Field From Defocused Monocular Video (ECCV 2024 · similarity 0.89)
- UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving (ICLR 2024 · similarity 0.88)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.87)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.87)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.87)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.87)
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.
