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

2026-04-05

AI Summary

This work addresses the limited robustness of 3D scene reconstruction under real-world adverse conditions such as extreme low light and smoke interference. To this end, the authors introduce RealX3D, the first benchmark specifically designed for such degraded scenarios, and organize a large-scale 3D reconstruction challenge. The benchmark encompasses key technical aspects including multimodal fusion, degradation modeling, robust feature extraction, and end-to-end reconstruction, enabling a systematic evaluation of methods submitted by 33 participating teams. The study not only achieves substantially improved reconstruction performance in harsh environments—with several entries significantly outperforming existing baselines—but also distills common design principles underlying highly robust 3D reconstruction approaches, offering valuable guidance for future research.

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.

Problem

• 3D restoration
• 3D reconstruction
• adverse conditions
• low-light
• smoke degradation

Innovation

• 3D restoration
• adverse conditions
• low-light reconstruction
• smoke-degraded environments
• RealX3D benchmark