Score: 0

RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction

Published: December 29, 2025 | arXiv ID: 2512.23437v1

By: Shuhong Liu , Chenyu Bao , Ziteng Cui and more

Potential Business Impact:

Fixes blurry 3D pictures from bad light.

Business Areas:
3D Technology Hardware, Software

We introduce RealX3D, a real-capture benchmark for multi-view visual restoration and 3D reconstruction under diverse physical degradations. RealX3D groups corruptions into four families, including illumination, scattering, occlusion, and blurring, and captures each at multiple severity levels using a unified acquisition protocol that yields pixel-aligned LQ/GT views. Each scene includes high-resolution capture, RAW images, and dense laser scans, from which we derive world-scale meshes and metric depth. Benchmarking a broad range of optimization-based and feed-forward methods shows substantial degradation in reconstruction quality under physical corruptions, underscoring the fragility of current multi-view pipelines in real-world challenging environments.

Country of Origin
πŸ‡―πŸ‡΅ Japan

Page Count
12 pages

Category
Computer Science:
CV and Pattern Recognition