mlsanityData to 7 Oct 2026

DehazeNeRF: Multiple Image Haze Removal and 3D Shape Reconstruction using Neural Radiance Fields

arXiv 2303.11364 ↗First posted 20 Mar 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Neural radiance fields (NeRFs) have demonstrated state-of-the-art performance for 3D computer vision tasks, including novel view synthesis and 3D shape reconstruction. However, these methods fail in adverse weather conditions. To address this challenge, we introduce DehazeNeRF as a framework that robustly operates in hazy conditions. DehazeNeRF extends the volume rendering equation by adding physically realistic terms that model atmospheric scattering. By parameterizing these terms using suitable networks that match the physical properties, we introduce effective inductive biases, which, together with the proposed regularizations, allow DehazeNeRF to demonstrate successful multi-view haze removal, novel view synthesis, and 3D shape reconstruction where existing approaches fail.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 30 of its 82 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

30 of 82 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  3. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  4. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  5. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  6. 2021Multi-Stage Progressive Image Restorationcited by 813
  7. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  9. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  10. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  11. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  12. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
18 more
  1. 2021Advances in Neural Renderingcited by 365
  2. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  3. 2020Multi-Scale Boosted Dehazing Network with Dense Feature Fusioncited by 229
  4. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
  5. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
  6. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  7. 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 121
  8. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 120
  9. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 113
  10. 2020Domain Adaptation for Image Dehazingcited by 108
  11. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  12. 2018Virtual Wave Optics for Non-Line-of-Sight Imagingcited by 54
  13. 2022NAN: Noise-Aware NeRFs for Burst-Denoisingcited by 48
  14. 2020Non-line-of-sight Imagingcited by 41
  15. 2020MPRNet: Multi-Path Residual Network for Lightweight Image Super Resolutioncited by 38
  16. 2022Volume Rendering Digest (for NeRF)cited by 31
  17. 2021Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazingcited by 2
  18. 2020Dehazing Cost Volume for Deep Multi-view Stereo in Scattering Media with Airlight and Scattering Coefficient Estimationcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 3.

10 papers.

  1. 2023SeaThru-NeRF: Neural Radiance Fields in Scattering Mediacited by 75
  2. 2024AONeuS: A Neural Rendering Framework for Acoustic-Optical Sensor Fusioncited by 13
  3. 2024RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Renderingcited by 8
  4. 2025SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstructioncited by 6
  5. 2025SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splattingcited by 5
  6. 2024RaFE: Generative Radiance Fields Restorationcited by 4
  7. 2024NeuroPump: Simultaneous Geometric and Color Rectification for Underwater Imagescited by 4
  8. 2025DehazeGS: Seeing Through Fog with 3D Gaussian Splattingcited by 4
  9. 2023Removing Adverse Volumetric Effects From Trained Neural Radiance Fieldscited by 1
  10. 2024Towards Degradation-Robust Reconstruction in Generalizable NeRFcited by 1