Research map / 3D vision / NeRF and radiance fields
Inverse Image-Based Rendering for Light Field Generation from Single Images
Hyunjun Jung, Hae-Gon Jeon
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 disparity positional encoding to the ray transformer (ablation) | iIBRnet · Pov-ray | PSNR: 12.008 -> 28.407 | Improved |
| add occlusion detection and diffusion inpainting with iterative ray update (ablation) | iIBRnet · Pov-ray | PSNR: 24.899 -> 28.407 | Improved |
| add entropy loss on rendering weights (ablation) | iIBRnet · Pov-ray | PSNR: 25.210 -> 28.407 | Improved |
| add EPI structure tensor loss (ablation) | iIBRnet · Pov-ray | PSNR: 26.910 -> 28.407 | Improved |
| swap depth foundation model (MiDaS, ZoeDepth, UniDepth instead of DepthAnythingV2) (ablation) | iIBRnet disparity prior · Pov-ray | PSNR: 27.990 / 28.310 / 28.372 vs 28.407 | No clear effect |
| fine-tune on target dataset instead of zero-shot | iIBR · Stanford | PSNR: 27.889 -> 27.682 PSNR; LPIPS 0.068 -> 0.052 | Mixed |
| fine-tune on NeRF LLFF instead of zero-shot | iIBR · NeRF LLFF | PSNR: 24.910 -> 25.534 | Improved |
| train iIBR on a different light field dataset than the test set | iIBR · Stanford test | PSNR: 27.682 (train Stanford) vs 27.889 (train Pov-ray) | Mixed |
| use iIBR instead of prior single-image NVS methods on NeRF LLFF | single-image novel view synthesis · NeRF LLFF | PSNR: 17.561 -> 24.910 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NViST — NViST: In the Wild New View Synthesis from a Single Image with Transformers (CVPR 2024) · better on 1 of 1 shared result
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
- Light Field Neural Rendering (CVPR 2022 · similarity 0.92)
- Neural Inverse Rendering from Propagating Light (CVPR 2025 · similarity 0.90)
- VMINer: Versatile Multi-view Inverse Rendering with Near- and Far-field Light Sources (CVPR 2024 · similarity 0.89)
- IllumiNeRF: 3D Relighting Without Inverse Rendering (NeurIPS 2024 · similarity 0.89)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.89)
- Latent Intrinsics Emerge from Training to Relight (NeurIPS 2024 · similarity 0.89)
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.
