Our datasets can be downloaded from https://drive.google.com/drive/folders/1TLj033oV0aplLE6xcQaSRcZpggDVTCHY?usp=sharing

Description: 

We used 24 3D mesh models from Free3D to create three datasets (eight models in each dataset). According to different difficulty levels, we name our datasets “easy”, “medium” and “hard”, respectively. Each 3D mesh model is first fixed at a certain position. A virtual range sensor with pre-set intrinsic parameters is then used to capture depth images at 1800–2500 different view points. At each view point, a 480x640 pixel depth image is generated by rendering the 3D mesh model using OpenGL Shading Language (GLSL). However, since the OpenGL rendering process applies linear interpolation by default, rendering surface normal images is infeasible. Hence, the surface normal of each triangle, constructed by three mesh vertices, is considered to be the ground truth surface normal of any 3D points residing on this triangle.