Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation

TL;DR

Shape2.5D is a large-scale dataset designed to improve depth and surface normal estimation for texture-less surfaces, supporting robust algorithm development through synthetic and real-world data.

Contribution

The paper introduces a comprehensive dataset specifically for texture-less surface reconstruction, including synthetic and real data, and provides benchmarks and an open-source data pipeline.

Findings

Supports development of robust depth and normal estimation algorithms

Enables voxel reconstruction from RGB images

Dataset is publicly available for research use

Abstract

Reconstructing texture-less surfaces poses unique challenges in computer vision, primarily due to the lack of specialized datasets that cater to the nuanced needs of depth and normals estimation in the absence of textural information. We introduce "Shape2.5D," a novel, large-scale dataset designed to address this gap. Comprising 1.17 million frames spanning over 39,772 3D models and 48 unique objects, our dataset provides depth and surface normal maps for texture-less object reconstruction. The proposed dataset includes synthetic images rendered with 3D modeling software to simulate various lighting conditions and viewing angles. It also includes a real-world subset comprising 4,672 frames captured with a depth camera. Our comprehensive benchmarks demonstrate the dataset's ability to support the development of algorithms that robustly estimate depth and normals from RGB images and perform voxel reconstruction. Our open-source data generation pipeline allows the dataset to be extended and adapted for future research. The dataset is publicly available at https://github.com/saifkhichi96/Shape25D.