RealX3D提供真实拍摄的多视角图像退化数据集，用于测试3D重建在真实环境下的鲁棒性。
RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction
- 构建统一采集流程，涵盖光照、散射、遮挡、模糊四类退化，分多严重等级
- 每场景含高分辨率图、RAW数据、激光扫描，生成世界尺度网格与精确深度图
- 实测现有方法在物理退化下性能显著下降，适合评估真实场景3D重建系统
我们提出RealX3D，一个基于真实拍摄的多视角视觉恢复与3D重建基准数据集，涵盖多种物理退化。退化分为四类：光照、散射、遮挡和模糊，并通过统一采集协议在多个严重程度下获取像素对齐的低质（LQ）与真值（GT）视图。每个场景包含高分辨率影像、RAW图像及密集激光扫描，据此构建世界尺度网格与度量深度图。对多种优化方法与前馈模型的基准测试表明，物理退化导致重建质量显著下降，凸显当前多视角流水线在真实复杂环境中的脆弱性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。