XA Bin-Picking is a point-cloud dataset comprising both simulated and real-world scenes with three industrial parts. Synthesized scenes consists of 1000 training samples. The test samples are real scenes and the ground truth instance labels are made manually. There are 20 to 30 identical types of parts randomly piled up in a scene. Each scene contains about 60,000 boundary points. Each point in the scene has instance annotations. The parts are texture-less and have no discernible color. Both of training samples and test sam- ples only contain the boundary points of parts.

Source: A Convolutional Neural Network for Point Cloud Instance Segmentation in Cluttered Scene Trained by Synthetic Data Without Color

Papers


Paper Code Results Date Stars

Dataset Loaders


No data loaders found. You can submit your data loader here.

Tasks


Similar Datasets