mlsanityData to 7 Oct 2026

Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark

arXiv 2607.29684 ↗First posted 31 Jul 2026cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Robust low-light imaging remains challenging for the community. Recent studies have explored fusing Near-Infrared (NIR) with noisy RGB to achieve improved enhancement, yet most methods depend on carefully curated training data pairs, with limited robustness under different scenarios. This paper offers a new perspective for RGB-NIR low-light imaging by incorporating 3D-aware neural modeling. Without using clean RGB supervision, a powerful model can be optimized to implicitly fuse extremely noisy RGB observations with NIR cues in 3D space, effectively recovering clean RGB images. The proposed model obviates the requirement for clean RGB data collection, generalizes across different noise levels. Extensive evaluations on synthetic and real data demonstrate its superiority. Codes available: https://github.com/MyNiuuu/3DarkFusion

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 31 Jul 2026.

Builds on

23 of 48 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  3. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  4. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  5. 2021Multi-Stage Progressive Image Restorationcited by 813
  6. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  7. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  8. 2019Real Image Denoising with Feature Attentioncited by 176
  9. 2014A* Samplingcited by 150
  10. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 104
  11. 2019Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusioncited by 78
  12. 2017Joint Image Filtering with Deep Convolutional Networkscited by 52
11 more
  1. 2022NAN: Noise-Aware NeRFs for Burst-Denoisingcited by 48
  2. 2018A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoisingcited by 42
  3. 2023Lighting up NeRF via Unsupervised Decomposition and Enhancementcited by 40
  4. 2023DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Priorcited by 19
  5. 2020Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environmentscited by 12
  6. 2024KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filtercited by 11
  7. 2024RS-NeRF: Neural Radiance Fields from Rolling Shutter Imagescited by 8
  8. 2023Visibility Constrained Wide-band Illumination Spectrum Design for Seeing-in-the-Darkcited by 7
  9. 2024Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoisingcited by 5
  10. 2024NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Datasetcited by 4
  11. 2024SGDFormer: One-stage Transformer-based Architecture for Cross-Spectral Stereo Image Guided Denoisingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026WorldSculpt: Generating Compositional Worlds from Grounded Videoscited by 2
  2. 2026Scanline-Aware Animatable Gaussian Avatars from Rolling-Shutter Videoscited by 0