Regularization of NeRFs using differential geometry
Not on the map. Why?
Abstract (arXiv)
Neural radiance fields, or NeRF, represent a breakthrough in the field of novel view synthesis and 3D modeling of complex scenes from multi-view image collections. Numerous recent works have shown the importance of making NeRF models more robust, by means of regularization, in order to train with possibly inconsistent and/or very sparse data. In this work, we explore how differential geometry can provide elegant regularization tools for robustly training NeRF-like models, which are modified so as to represent continuous and infinitely differentiable functions. In particular, we present a generic framework for regularizing different types of NeRFs observations to improve the performance in challenging conditions. We also show how the same formalism can also be used to natively encourage the regularity of surfaces by means of Gaussian or mean curvatures.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 29 Jun 2022.
Builds on
27 of 43 references.
References · 27
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
- 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
- 2021Volume Rendering of Neural Implicit Surfacescited by 990
- 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
- 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
- 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
- 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
15 more
- 2020Implicit Geometric Regularization for Learning Shapescited by 707
- 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
- 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
- 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
- 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
- 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
- 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
- 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
- 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
- 2020State of the Art on Neural Renderingcited by 276
- 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
- 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 180
- 2021LOLNeRF: Learn from One Lookcited by 84
- 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
- 2022Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Camerascited by 59
Built on by
Citing papers per year: 2023: 1; 2024: 2.
3 papers.