Addressing the Shape-Radiance Ambiguity in View-Dependent Radiance Fields
Not on the map. Why?
Abstract (arXiv)
We present a method for handling view-dependent information in radiance fields to help with convergence and quality of 3D reconstruction. Radiance fields with view-dependence suffers from the so called shape-radiance ambiguity, which can lead to incorrect geometry given a high angular resolution of view-dependent colors. We propose the addition of a difference plane in front of each camera, with the purpose of separating view-dependent and Lambertian components during training. We also propose an additional step where we train, but do not store, a low-resolution view-dependent function that helps to isolate the surface if such a separation is proven difficult. These additions have a small impact on performance and memory usage but enables reconstruction of scenes with highly specular components without any other explicit handling of view-dependence such as Spherical Harmonics.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 30 references that are in the map. First posted on arXiv 3 Mar 2022.
Builds on
18 of 30 references.
References · 18
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
- 2020Neural Sparse Voxel Fieldscited by 959
- 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
- 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
- 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
- 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
- 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
- 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
6 more
- 2020State of the Art on Neural Renderingcited by 278
- 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
- 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
- 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
- 2017A Survey of Structure from Motioncited by 158
- 2021PERF: Performant, Explicit Radiance Fieldscited by 5
Built on by
Citing papers per year: 2023: 2.
2 papers.