# Benchmarking Robustness in Neural Radiance Fields

arXiv: https://arxiv.org/abs/2301.04075 · HTML: https://mlsanity.com/paper/2301.04075/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 60 references that are in the map.
- First posted on arXiv 10 Jan 2023.

## Builds on (most cited first, 30 of 39)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [Free View Synthesis](https://mlsanity.com/paper/2008.05511/) (2020)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [Pushing the Boundaries of View Extrapolation with Multiplane Images](https://mlsanity.com/paper/1905.00413/) (2019)
- [Deblur-NeRF: Neural Radiance Fields from Blurry Images](https://mlsanity.com/paper/2111.14292/) (2021)
- [Stable View Synthesis](https://mlsanity.com/paper/2011.07233/) (2020)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)

## Built on by (most cited first, 13 of 13)

- [Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views](https://mlsanity.com/paper/2303.15206/) (2023)
- [Digging into Depth Priors for Outdoor Neural Radiance Fields](https://mlsanity.com/paper/2308.04413/) (2023)
- [NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations](https://mlsanity.com/paper/2306.06359/) (2023)
- [CrossScore: Towards Multi-View Image Evaluation and Scoring](https://mlsanity.com/paper/2404.14409/) (2024)
- [Benchmarking Image Similarity Metrics for Novel View Synthesis Applications](https://mlsanity.com/paper/2506.12563/) (2025)
- [Shielding the Unseen: Privacy Protection through Poisoning NeRF with Spatial Deformation](https://mlsanity.com/paper/2310.03125/) (2023)
- [RoHOI: Robustness Benchmark for Human-Object Interaction Detection](https://mlsanity.com/paper/2507.09111/) (2025)
- [Towards a Robust Framework for NeRF Evaluation](https://mlsanity.com/paper/2305.18079/) (2023)
- [Removing Adverse Volumetric Effects From Trained Neural Radiance Fields](https://mlsanity.com/paper/2311.10523/) (2023)
- [Towards Degradation-Robust Reconstruction in Generalizable NeRF](https://mlsanity.com/paper/2411.11691/) (2024)
- [PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems](https://mlsanity.com/paper/2604.16540/) (2026)
- [Enhancing Neural Rendering Methods with Image Augmentations](https://mlsanity.com/paper/2306.08904/) (2023)
- [Beyond Anonymization: Object Scrubbing for Privacy-Preserving 2D and 3D Vision Tasks](https://mlsanity.com/paper/2504.16557/) (2025)

## Abstract (arXiv)

Neural Radiance Field (NeRF) has demonstrated excellent quality in novel view synthesis, thanks to its ability to model 3D object geometries in a concise formulation. However, current approaches to NeRF-based models rely on clean images with accurate camera calibration, which can be difficult to obtain in the real world, where data is often subject to corruption and distortion. In this work, we provide the first comprehensive analysis of the robustness of NeRF-based novel view synthesis algorithms in the presence of different types of corruptions. We find that NeRF-based models are significantly degraded in the presence of corruption, and are more sensitive to a different set of corruptions than image recognition models. Furthermore, we analyze the robustness of the feature encoder in generalizable methods, which synthesize images using neural features extracted via convolutional neural networks or transformers, and find that it only contributes marginally to robustness. Finally, we reveal that standard data augmentation techniques, which can significantly improve the robustness of recognition models, do not help the robustness of NeRF-based models. We hope that our findings will attract more researchers to study the robustness of NeRF-based approaches and help to improve their performance in the real world.