Research map / 3D vision / NeRF and radiance fields
IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis
Weicai Ye, Shuo Chen, Chong Bao, Hujun Bao, Marc Pollefeys, Zhaopeng Cui, Guofeng Zhang
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 intrinsic decomposition heads to NeRF | NeRF · Blender Object dataset | PSNR (novel view synthesis): 31.0838 -> 30.7230 | No clear effect |
| add intrinsic heads to Semantic-NeRF | Semantic-NeRF · Replica Scene dataset | PSNR / mIoU: PSNR 30.9770 -> 30.7044; mIoU 0.9725 -> 0.9702 | No clear effect |
| add intrinsic prior and iterative reflectance clustering (ablation) | IntrinsicNeRF baseline · Blender Object dataset | reflectance accuracy | Mixed |
| use hierarchical clustering with semantic constraints instead of plain reflectance clustering (ablation) | IntrinsicNeRF · Replica Scene | reflectance boundaries (qualitative) | Improved |
| apply IntrinsicNeRF to outdoor EDEN scenes | IntrinsicNeRF · EDEN dataset | reflectance PSNR: 15.4692 vs CGIntrinsic 17.9740 | Hurt |
| add reflectance clustering during training | IntrinsicNeRF · Blender Object training time | training time: NeRF 5.4h -> Ours 6.5h; clustering 39s every 10K iterations | Mixed |
Closest papers by meaning
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs (CVPR 2022 · similarity 0.91)
- Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis (ICCV 2023 · similarity 0.91)
- PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields (CVPR 2023 · similarity 0.90)
- AdaNeRF: Adaptive Sampling for Real-Time Rendering of Neural Radiance Fields (ECCV 2022 · similarity 0.90)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.89)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · 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.
