5 datasets found

A custom Blender code is used to generate labeled training images containing the rendered CAD model in context. Then, a pretrained object detection model is fine-tuned on the...

The Scan2CAD dataset contains object-level human-generated annotations. The annotations include category label, segmentation, a similar CAD model in ShapeNet, and the...

A new 3D dataset, CC3D, a collection of 50k+ aligned pairs of meshes, a CAD model and its virtually 3D scanned counterpart with corresponding scanning artifacts.

3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone,...

Point cloud registration is a crucial problem in computer vision and robotics. Existing methods either rely on matching local geometric features, which are sensitive to the pose...