Research map / 3D vision / NeRF and radiance fields
ORCa: Glossy Objects As Radiance-Field Cameras
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 ORCa's 5D environment radiance field and virtual-cone formulation instead of Ref-NeRF | Glossy-object reflection reconstruction · D1 (globe) | specular radiance PSNR (dB): 14.88 -> 16.64 | Helped |
| Use ORCa's 5D environment radiance field and virtual-cone formulation instead of PANDORA | Glossy-object reflection reconstruction · D2 (Pokemon) | specular radiance PSNR (dB): 17.76 -> 18.98 | Helped |
| Use ORCa instead of the strongest baseline | Glossy-object reflection reconstruction · D1 (globe) | normals MAE (°): 2.387 -> 1.873 | Helped |
| Use ORCa instead of the strongest baseline | Glossy-object reflection reconstruction · D2 (Pokemon) | normals MAE (°): 3.693 -> 3.568 | Helped |
| Use ORCa instead of Ref-NeRF | Glossy-object reflection reconstruction · D1 (globe) | mixed radiance PSNR (dB): 19.58 -> 18.23 | Hurt |
| Use ORCa instead of PANDORA | Glossy-object reflection reconstruction · D2 (Pokemon) | mixed radiance PSNR (dB): 22.73 -> 22.31 | Hurt |
| Model the environment as a 5D radiance field rather than a flat 2D environment map | ORCa · Scenes with nearby occluders | beyond-field-of-view novel-view synthesis | Helped |
| Use the proposed physically based virtual-cone origins and compute cone radius rather than placing cone origins at the surface intersection (ablation) | ORCa · Rendered scenes | specular radiance estimation | Helped |
| Use the proposed physically based virtual-cone origins and compute cone radius rather than placing cone origins at the surface intersection (ablation) | ORCa · Rendered scenes | surface-normal smoothness | Helped |
Closest papers by meaning
- Seeing the World through Your Eyes (CVPR 2024 · similarity 0.87)
- Glossy Object Reconstruction with Cost-effective Polarized Acquisition (CVPR 2025 · similarity 0.85)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · similarity 0.85)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.85)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.85)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.85)
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.