OLATverse：一个具有精确光照控制的大规模真实世界物体数据集
OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control
为物体级逆渲染、重光照与法线估计提供首个大规模真实世界基准，含精确标定的相机参数、物体掩码、光度法线与漫反射反照率，可直接用于训练与评测真实场景下的分解式渲染方法。
原文依据 establishing the first comprehensive real-world object-centric benchmark for inverse rendering and normal estimation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 OLATverse，一个包含约 900 万张图像的大规模数据集，覆盖 765 个真实世界物体，在多种精确控制的光照条件下从多个视角采集。尽管近期以物体为中心的逆渲染、新视角合成与重光照研究已取得令人鼓舞的结果，但多数技术仍严重依赖合成数据集进行训练、依赖小规模真实数据集进行基准评测，这限制了其真实感与泛化能力。为弥补这一空白，OLATverse 相较现有数据集具有两项关键优势：对真实物体的大规模覆盖，以及精确控制光照下的高保真外观。具体而言，OLATverse 包含 765 个常见与罕见的真实世界物体，涵盖广泛的材质类别。每个物体使用 35 台单反相机与 331 个独立控制的光源进行采集，从而能够模拟多样的光照条件。此外，我们为每个物体提供经过良好标定的相机参数、精确的物体掩码、光度表面法线以及漫反射反照率作为辅助资源。我们还构建了大规模的评测集，建立了首个面向逆渲染与法线估计的综合性真实世界物体级基准。OLATverse 已在 https://vcai.mpi-inf.mpg.de/projects/OLATverse/ 公开可用。
英文原文摘要 1384 字符
We introduce OLATverse, a large-scale dataset comprising around 9M images of 765 real-world objects, captured from multiple viewpoints under a diverse set of precisely controlled lighting conditions. While recent advances in object-centric inverse rendering, novel view synthesis and relighting have shown promising results, most techniques still heavily rely on the synthetic datasets for training and small-scale real-world datasets for benchmarking, which limits their realism and generalization. To address this gap, OLATverse offers two key advantages over existing datasets: large-scale coverage of real objects and high-fidelity appearance under precisely controlled illuminations. Specifically, OLATverse contains 765 common and uncommon real-world objects, spanning a wide range of material categories. Each object is captured using 35 DSLR cameras and 331 individually controlled light sources, enabling the simulation of diverse illumination conditions. In addition, for each object, we provide well-calibrated camera parameters, accurate object masks, photometric surface normals, and diffuse albedo as auxiliary resources. We also construct an extensive evaluation set, establishing the first comprehensive real-world object-centric benchmark for inverse rendering and normal estimation. OLATverse is publicly available at https://vcai.mpi-inf.mpg.de/projects/OLATverse/.