构建首个统一评测多视角3D重建的实测数据集，覆盖多种光照与视角条件。
EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups
- 设计包含25个物体、8500张图像的多视角偏振成像数据集
- 在17种光照下实现高保真表面重建，验证13种方法性能差异
- 适合研究多视角3D重建、偏振感知建模与真实场景评估的学者
神经表面重建的进展显著提升了三维重建质量。然而，现有真实世界数据集主要针对基于RGB输入的多视角立体（MVS）进行评测。多视角光度偏振（MVPS）和多视角偏振形状恢复（MVSfP）虽在高保真表面重建与稀疏输入场景中至关重要，却未与MVS一起被量化评估。为明确不同MVX（MVS、MVSfP、MVPS）技术的工作范围，我们提出EvalMVX，一个包含25个物体的真实世界数据集，每个物体在20个不同视角和17种光照条件（包括OLAT与自然光照）下由偏振相机捕获，共生成8,500张图像，并提供对齐的地面真值3D网格，支持对各类MVX方法的同步定量评测。基于EvalMVX，我们评估了近五年发布的13种MVX方法，记录最佳表现模型，并识别出在不同几何细节与反射类型下的开放问题。我们希望EvalMVX及评测结果能推动未来多视角3D重建研究。
原文摘要 · Abstract (English)
Recent advancements in neural surface reconstruction have significantly enhanced 3D reconstruction. However, current real world datasets mainly focus on benchmarking multiview stereo (MVS) based on RGB inputs. Multiview photometric stereo (MVPS) and multiview shape from polarization (MVSfP), though indispensable on high-fidelity surface reconstruction and sparse inputs, have not been quantitatively assessed together with MVS. To determine the working range of different MVX (MVS, MVSfP, and MVPS) techniques, we propose EvalMVX, a real-world dataset containing $25$ objects, each captured with a polarized camera under $20$ varying views and $17$ light conditions including OLAT and natural illumination, leading to $8,500$ images. Each object includes aligned ground-truth 3D mesh, facilitating quantitative benchmarking of MVX methods simultaneously. Based on our EvalMVX, we evaluate $13$ MVX methods published in recent years, record the best-performing methods, and identify open problems under diverse geometric details and reflectance types. We hope EvalMVX and the benchmarking results can inspire future research on multiview 3D reconstruction.
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。