Sorry, you need to enable JavaScript to visit this website.

Point cloud segmentation is a key problem of 3D multimedia signal processing. Existing methods usually use single network structure which is trained by per-point loss. These methods mainly focus on geometric similarity between the prediction results and the ground truth, ignoring visual perception difference. In this paper, we present a segmentation adversarial network to overcome the drawbacks above. Discriminator is introduced to provide a perceptual loss to increase the rationality judgment of prediction and guide the further optimization of the segmentator.