High-quality 3D ground-truth shapes are critical for 3D object reconstruction evaluation. However, it is difficult to create a replica of an object in reality, and even 3D reconstructions generated by 3D scanners have artefacts that cause biases in evaluation. To address this issue, we introduce a novel multi-view RGBD dataset captured using a mobile device, which includes highly precise 3D ground-truth annotations for 153 object models featuring a diverse set of 3D structures. We obtain precise 3D ground-truth shape without relying on high-end 3D scanners by utilising LEGO models with known geometry as the 3D structures for image capture. The distinct data modality offered by high-resolution RGB images and low-resolution depth maps captured on a mobile device, when combined with precise 3D geometry annotations, presents a unique opportunity for future research on high-fidelity 3D reconstruction. Furthermore, we evaluate a range of 3D reconstruction algorithms on the proposed dataset. Project page: http://code.active.vision/MobileBrick/
翻译:高质量的 3D 地面真相形状对于 3D 对象重建评估至关重要。 但是,很难在现实中复制一个物体,甚至3D 扫描器生成的3D 重建也有导致评价偏差的人工制品。为了解决这一问题,我们引入了使用移动设备采集的新颖的多视图 RGBD 数据集,其中包括由一组3D 结构组成的153 个目标模型的高度精确的 3D 地面真相说明。我们通过使用称为3D 图像捕获结构的GEGO 模型,在不依赖高端 3D 扫描仪的情况下获得精确的 3D 地面真相形状。高分辨率 RGB 图像和在移动设备上捕获的低分辨率深度地图提供的独特数据模式,加上精确的 3D 几何说明,为今后对高纤维 3D 重建进行研究提供了独特的机会。此外,我们评估了拟议数据集上的一系列3D 重建算法。项目网页: http://codection. vision/MobileBrick/</s>