Research map / 3D vision / NeRF and radiance fields
Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis
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 |
|---|---|---|---|
| apply cross-guided optimization with SwinIR features, rendered train-view images, and uncertainty maps | SwinIR-based CROP · Synthetic NeRF | PSNR: 30.5072 -> 30.7140 (NVS); 33.2345 -> 33.7725 (MVSR) | Helped |
| apply cross-guided optimization with SwinIR features, rendered train-view images, and uncertainty maps | SwinIR-based CROP · BlendedMVS | PSNR: 26.5795 -> 26.6914 (NVS); 29.6916 -> 29.7451 (MVSR) | Helped |
| apply cross-guided optimization with SwinIR features, rendered train-view images, and uncertainty maps | SwinIR-based CROP · Tanks and Temples | PSNR: 28.5973 -> 28.6490 (NVS); 35.7584 -> 36.2430 (MVSR) | Helped |
| update SR outputs without rendered train-view RGB guidance (ablation) | SwinIR on Synthetic NeRF · Synthetic NeRF | PSNR: 30.4878 -> 30.4241 (NVS); 33.1234 -> 32.9417 (MVSR) | Hurt |
| add rendered train-view RGB guidance to one SUM update (ablation) | SwinIR on Synthetic NeRF · Synthetic NeRF | PSNR: 30.4241 -> 30.6501 (NVS); 32.9417 -> 33.6402 (MVSR) | Helped |
| add rendered uncertainty maps with rendered RGB and three SUM updates (ablation) | SwinIR-based CROP on Synthetic NeRF · Synthetic NeRF | PSNR: 30.6824 -> 30.7140 (NVS); 33.5945 -> 33.7725 (MVSR) | Helped |
| use three rather than one update with rendered RGB and uncertainty maps (ablation) | SwinIR-based CROP on Synthetic NeRF · Synthetic NeRF | PSNR: 30.6554 -> 30.7140 (NVS); 33.7112 -> 33.7725 (MVSR) | Helped |
Closest papers by meaning
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.89)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.88)
- MuRF: Multi-Baseline Radiance Fields (CVPR 2024 · similarity 0.87)
- Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis? (CVPR 2024 · similarity 0.87)
- UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving (ICLR 2024 · similarity 0.87)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 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.