mlsanityData to 14 Oct 2026

NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results

arXiv 2604.04135 ↗First posted 5 Apr 2026cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to identify robust reconstruction pipelines that are robust under real-world adverse conditions, specifically extreme low-light and smoke-degraded environments, as captured by our RealX3D benchmark. A total of 279 participants registered for the competition, of whom 33 teams submitted valid results. We thoroughly evaluate the submitted approaches against state-of-the-art baselines, revealing significant progress in 3D reconstruction under adverse conditions. Our analysis highlights shared design principles among top-performing methods and provides insights into effective strategies for handling 3D scene degradation.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 43 of its 79 references that are in the map. First posted on arXiv 5 Apr 2026.

Builds on

43 of 79 references.

References · 43

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  4. 2024Depth Anything V2cited by 1,422
  5. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  6. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  7. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  8. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 542
  9. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  10. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 261
  11. 2022Vision Transformers for Single Image Dehazingcited by 260
  12. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 231
31 more
  1. 2024A Survey on 3D Gaussian Splattingcited by 224
  2. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 221
  3. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  4. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 161
  5. 20243D Gaussian as a New Era: A Surveycited by 104
  6. 2024SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMcited by 87
  7. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 86
  8. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  9. 2023SeaThru-NeRF: Neural Radiance Fields in Scattering Mediacited by 75
  10. 2025HVI: A New Color Space for Low-light Image Enhancementcited by 63
  11. 2024DarkIR: Robust Low-Light Image Restorationcited by 48
  12. 2024MaIR: A Locality- and Continuity-Preserving Mamba for Image Restorationcited by 45
  13. 2024WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splattingcited by 41
  14. 2023Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumptioncited by 35
  15. 2025Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustmentcited by 27
  16. 2026The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Reportcited by 25
  17. 2025DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Imagescited by 24
  18. 2024MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesiscited by 22
  19. 2025LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priorscited by 21
  20. 2024DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environmentscited by 19
  21. 2025RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstructioncited by 19
  22. 2025I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactionscited by 17
  23. 2026Faster-GS: Analyzing and Improving Gaussian Splatting Optimizationcited by 17
  24. 2025DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Priorcited by 14
  25. 2024Efficient Diffusion as Low Light Enhancercited by 13
  26. 2026GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Modelcited by 11
  27. 2026Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imagingcited by 8
  28. 2026Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesiscited by 8
  29. 20253D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decouplingcited by 5
  30. 2026UDPNet: Unleashing Depth-based Priors for Robust Image Dehazingcited by 3
  31. 2025Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Reportcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 11.

11 papers.