# NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images

arXiv: https://arxiv.org/abs/2111.13679 · HTML: https://mlsanity.com/paper/2111.13679/

## Key facts

- Cited by 336 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 60 references that are in the map.
- First posted on arXiv 26 Nov 2021.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [Free View Synthesis](https://mlsanity.com/paper/2008.05511/) (2020)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [DeepStereo: Learning to Predict New Views from the World's Imagery](https://mlsanity.com/paper/1506.06825/) (2015)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Stable View Synthesis](https://mlsanity.com/paper/2011.07233/) (2020)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [Burst Denoising with Kernel Prediction Networks](https://mlsanity.com/paper/1712.02327/) (2017)
- [NeRF--: Neural Radiance Fields Without Known Camera Parameters](https://mlsanity.com/paper/2102.07064/) (2021)
- [T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis](https://mlsanity.com/paper/2109.15271/) (2021)
- [Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes](https://mlsanity.com/paper/2003.14013/) (2020)
- [Synthetic Depth-of-Field with a Single-Camera Mobile Phone](https://mlsanity.com/paper/1806.04171/) (2018)
- [Mobile Computational Photography: A Tour](https://mlsanity.com/paper/2102.09000/) (2021)
- [Deep Burst Denoising](https://mlsanity.com/paper/1712.05790/) (2017)

## Built on by (most cited first, 30 of 336)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions](https://mlsanity.com/paper/2303.12789/) (2023)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization](https://mlsanity.com/paper/2303.07418/) (2023)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024)
- [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023)
- [3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos](https://mlsanity.com/paper/2403.01444/) (2024)
- [Instant Volumetric Head Avatars](https://mlsanity.com/paper/2211.12499/) (2022)
- [NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)](https://mlsanity.com/paper/2210.00379/) (2022)
- [ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields](https://mlsanity.com/paper/2211.11704/) (2022)
- [NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields](https://mlsanity.com/paper/2210.15947/) (2022)
- [SparseGS: Sparse View Synthesis using 3D Gaussian Splatting](https://mlsanity.com/paper/2312.00206/) (2023)
- [Generalizable Patch-Based Neural Rendering](https://mlsanity.com/paper/2207.10662/) (2022)
- [RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos](https://mlsanity.com/paper/2401.12592/) (2024)
- [HDR-NeRF: High Dynamic Range Neural Radiance Fields](https://mlsanity.com/paper/2111.14451/) (2021)
- [Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting](https://mlsanity.com/paper/2403.15530/) (2024)
- [3D Gaussian as a New Era: A Survey](https://mlsanity.com/paper/2402.07181/) (2024)
- [Progressively Optimized Local Radiance Fields for Robust View Synthesis](https://mlsanity.com/paper/2303.13791/) (2023)
- [RobustNeRF: Ignoring Distractors with Robust Losses](https://mlsanity.com/paper/2302.00833/) (2023)
- [EventNeRF: Neural Radiance Fields from a Single Colour Event Camera](https://mlsanity.com/paper/2206.11896/) (2022)
- [VR-NeRF: High-Fidelity Virtualized Walkable Spaces](https://mlsanity.com/paper/2311.02542/) (2023)
- [BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields](https://mlsanity.com/paper/2211.12853/) (2022)
- [Deforming Radiance Fields with Cages](https://mlsanity.com/paper/2207.12298/) (2022)
- [Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing](https://mlsanity.com/paper/2211.03017/) (2022)
- [SeaThru-NeRF: Neural Radiance Fields in Scattering Media](https://mlsanity.com/paper/2304.07743/) (2023)

## Abstract (arXiv)

Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis from a collection of posed input images. Like most view synthesis methods, NeRF uses tonemapped low dynamic range (LDR) as input; these images have been processed by a lossy camera pipeline that smooths detail, clips highlights, and distorts the simple noise distribution of raw sensor data. We modify NeRF to instead train directly on linear raw images, preserving the scene's full dynamic range. By rendering raw output images from the resulting NeRF, we can perform novel high dynamic range (HDR) view synthesis tasks. In addition to changing the camera viewpoint, we can manipulate focus, exposure, and tonemapping after the fact. Although a single raw image appears significantly more noisy than a postprocessed one, we show that NeRF is highly robust to the zero-mean distribution of raw noise. When optimized over many noisy raw inputs (25-200), NeRF produces a scene representation so accurate that its rendered novel views outperform dedicated single and multi-image deep raw denoisers run on the same wide baseline input images. As a result, our method, which we call RawNeRF, can reconstruct scenes from extremely noisy images captured in near-darkness.