mIoU: 55.0
Papers with Code · CC BY-SA 4.0
3D Semantic Segmentation
3D Semantic Segmentation is a computer vision task that involves dividing a 3D point cloud or 3D mesh into semantically meaningful parts or regions. The goal of 3D semantic segmentation is to identify and label different objects and parts within a 3D scene, which can be used for applications such as robotics, autonomous driving, and augmented reality.
논문
mIoU: 57.0
mIoU-1%: 57
mean Corruption Error (mCE): 98.72%
mIoU: 42.66
mIOU: 53.8
mIOU: 62.1
mIOU: 45.1
mIoU (6-Fold): 76.0mAcc: 85.8
mIoU: 61.7
mIOU: 58.2
mIoU: 62.30oAcc: 93.7
mIoU: 57.58
mIoU: 37.29
mIoU: 63.4
mIoU (6-Fold): 75.0mIoU (Area-5): 72.4
mIOU: 43.2
mIoU (6-Fold): 73.5mIoU (Area-5): 70.4
mIoU (Area-5): 71.6
mIoU (6-Fold): 58.98
mIoU (6-Fold): 74.9mIoU (Area-5): 70.5
mIoU: 55.1
mIoU: 61.3
mIoU: 33.30
mIOU: 60.8