Research map / 3D vision / NeRF and radiance fields
NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 NoPe-NeRF instead of BARF | Unposed NeRF · ScanNet mean | PSNR: 31.41 -> 31.86 | Helped |
| Use NoPe-NeRF instead of SC-NeRF | Unposed NeRF · Tanks and Temples mean | PSNR: 23.76 -> 26.34 | Helped |
| Use NoPe-NeRF instead of SC-NeRF | Unposed NeRF · ScanNet mean | RPE_r: 0.522 -> 0.180 | Helped |
| Use NoPe-NeRF instead of BARF | Unposed NeRF · Tanks and Temples mean | RPE_r: 0.441 -> 0.038 | Helped |
| Add learnable scale and shift parameters for each monocular depth map (ablation) | NoPe-NeRF · ScanNet | RPE_t: 1.929 -> 0.801 | Helped |
| Add pairwise point cloud loss L_pc (ablation) | NoPe-NeRF · ScanNet | RPE_t: 2.227 -> 0.801 | Helped |
| Add surface-based photometric loss L_rgb-s (ablation) | NoPe-NeRF · ScanNet | RPE_t: 1.814 -> 0.801 | Helped |
| Add depth loss L_depth (ablation) | NoPe-NeRF · ScanNet | RPE_t: 1.498 -> 0.801 | Helped |
| Use a two-stage procedure that reinitialises NeRF and retrains with optimised poses | NoPe-NeRF · ScanNet mean | PSNR: 31.86 -> 31.88 | Mixed |
Closest papers by meaning
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.94)
- AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization (AAAI 2024 · similarity 0.92)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.91)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.91)
- ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization (CVPR 2024 · similarity 0.91)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · 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.