Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shuhong Liu, Chenyu Bao, Ziteng Cui, Xuangeng Chu, Bin Ren, Lin Gu, Xiang Chen, Mingrui Li, Long Ma, Marcos V. Conde, Radu Timofte, Yun Liu, Ryo Umagami, Tomohiro Hashimoto, Zijian Hu, Yuan Gan, Tianhan Xu, Yusuke Kurose, Tatsuya Harada, Junwei Yuan, Gengjia Chang, Xining Ge, Mache You, Qida Cao, Zeliang Li, Xinyuan Hu, Hongde Gu, Changyue Shi, Jiajun Ding, Zhou Yu, Jun Yu, Seungsang Oh, Fei Wang, Donggun Kim, Zhiliang Wu, Seho Ahn, Xinye Zheng, Kun Li, Yanyan Wei, Weisi Lin, Dizhe Zhang, Yuchao Chen, Meixi Song, Hanqing Wang, Haoran Feng, Lu Qi, Jiaao Shan, Yang Gu, Jiacheng Liu, Shiyu Liu, Kui Jiang, Junjun Jiang, Runyu Zhu, Sixun Dong, Qingxia Ye, Zhiqiang Zhang, Zhihua Xu, Zhiwei Wang, Phan The Son, Zhimiao Shi, Zixuan Guo, Xueming Fu, Lixia Han, Changhe Liu, Zhenyu Zhao, Manabu Tsukada, Zheng Zhang, Zihan Zhai, Tingting Li, Ziyang Zheng, Yuhao Liu, Dingju Wang, Jeongbin You, Younghyuk Kim, Il-Youp Kwak, Mingzhe Lyu, Junbo Yang, Wenhan Yang, Hongsen Zhang, Jinqiang Cui, Hong Zhang, Haojie Guo, Hantang Li, Qiang Zhu, Bowen He, Xiandong Meng, Debin Zhao, Xiaopeng Fan, Wei Zhou, Linzhe Jiang, Linfeng Li, Louzhe Xu, Qi Xu, Hang Song, Chenkun Guo, Weizhi Nie, Yufei Li, Xingan Zhan, Zhanqi Shi, Dufeng Zhang, Boyuan Tian, Jingshuo Zeng, Gang He, Yubao Fu, Weijie Wang, Cunchuan Huang

Abstract

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.

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

Abstract

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.

Paper Structure

This paper contains 36 sections, 28 figures, 1 table.

Table of Contents

  1. Introduction
  2. Tracks and Competition
  3. Track 1: 3D Lowlight Enhancement
  4. FuME-GS: Fusion-Guided Multi-Stage Enhancement for 3DGS
  5. CISP-GS: Multi-Branch GS with ISP Supervision and Frequency-Split Target Fusion
  6. TCIDNet-IBGS
  7. IDEAL: Illumination Disentanglement and Enhancement for 3D Low-Light Reconstruction
  8. NAKA-GS: A Bionics-inspired Dual-Branch Naka Correlation and Progressive Point Pruning for Low-Light 3DGS
  9. GREP-GS: Global-Residual Decomposition with Hybrid Edge Prior for Low-Light 3DGS
  10. IC-GS: Illumination-Calibrated 3DGS
  11. Space-GS
  12. ELoG-GS: Extreme Low-light Optimized Gaussian Splatting
  13. AdaTone-GS
  14. SLL-GS: Staged Low-Light 3DGS
  15. GammaGS: Gamma-Calibrated 3D Gaussian Splatting with Affine Color Correction
  16. ...and 21 more sections

Figures (28)

  • Figure 1: Visualizations of clean-degraded pairs in Track 1 & 2. Each track features 7 distinct scenes from the RealX3D benchmark liu2025realx3d.
  • Figure 2: Overview of the proposed Fusion-Guided Multi-Stage Enhancement for 3DGS.
  • Figure 3: Overall architecture of the proposed multi-branch low-light 3DGS framework.
  • Figure 4: Overview of the proposed TCIDNet-IBGS.
  • Figure 5: Overall architecture of IDEAL. The Appearance MLP predicts Gain and Bias maps to absorb view-dependent artifacts from Pseudo RGB during training, supervised by $\mathcal{L}_{color}$ and $\mathcal{L}_{depth}$. At inference, the Appearance MLP is discarded and only the clean Base 3DGS is retained for rendering.
  • ...and 23 more figures