Research map / 3D vision / NeRF and radiance fields
Self-Calibrating Neural Radiance Fields
Yoonwoo Jeong, Seokjun Ahn, Christopher Choy, Anima Anandkumar, Minsu Cho, Jaesik Park
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 learnable intrinsic and extrinsic camera parameters (ablation) | NeRF · LLFF Fortress | PSNR: 30.5 -> 35.3 | Improved |
| add learnable intrinsic and extrinsic camera parameters (ablation) | NeRF · LLFF Room | PSNR: 31.5 -> 38.3 | Improved |
| add learnable non-linear ray distortion (ablation) | NeRF + IE · LLFF Fortress | PSNR: 35.3 -> 36.4 | Improved |
| add learnable non-linear ray distortion (ablation) | NeRF + IE · LLFF Room | PSNR: 38.3 -> 39.4 | Improved |
| add projected ray distance loss (ablation) | NeRF + IE + OD · LLFF Fortress | PSNR: 36.4 -> 36.6 | Improved |
| add projected ray distance loss (ablation) | NeRF + IE + OD · LLFF Room | PSNR: 39.4 -> 39.7 | Improved |
| add projected ray distance loss (ablation) | NeRF + IE + OD · LLFF Fern | PSNR: 30.9 -> 31.1 | Improved |
| add projected ray distance loss (ablation) | NeRF + IE + OD · LLFF Flower | PSNR: 33.1 -> 33.3 | Improved |
| self-calibrate camera without COLMAP initialization versus plain NeRF (ablation) | NeRF · LLFF Flower | PSNR: 13.8 -> 33.2 | Improved |
| add self-calibration on top of COLMAP-initialized cameras (ablation) | NeRF · LLFF Fortress | PSNR: 35.3 -> 36.6 | Improved |
| add self-calibration with radial distortion (fish-eye) (ablation) | NeRF++[RD] · Fish-eye Globe | PSNR: 21.97 -> 23.76 | Improved |
| add self-calibration on top of COLMAP cameras (ablation) | NeRF++ · Tanks and Temples Truck | PSNR: 24.13 -> 25.22 | Improved |
Closest papers by meaning
- Revisiting Calibration of Wide-Angle Radially Symmetric Cameras (ECCV 2024 · similarity 0.89)
- AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025 · similarity 0.88)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.88)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.88)
- UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving (ICLR 2024 · similarity 0.87)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · 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.
