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

TL;DR

RealX3D is a comprehensive real-world benchmark dataset for multi-view 3D reconstruction and visual restoration that highlights the challenges posed by physical degradations like illumination, scattering, occlusion, and blurring.

Contribution

It introduces a new dataset with diverse physical corruptions, multi-level severity, and high-quality ground truth, enabling robust evaluation of reconstruction methods in real-world conditions.

Findings

Current methods degrade significantly under physical corruptions.

Benchmark reveals fragility of existing multi-view reconstruction pipelines.

Dataset facilitates development of more robust algorithms.

Abstract

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.