miou Val: 64.1Model size: 37.9M
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
Mean IoU (class): 46.07
mIoU: 73.3
miou: 58.3mIoU Category: 73.66miou Val: 57.8Model size: 41.2M
mIoU: 45.43mIoU (test): 45.34
Top-1 IoU: 0.445Top-3 IoU: 0.688
Mean IoU (class): 43.07
mIoU: 78.3%
mIoU: 62.0
Top-1 IoU: 0.456Top-3 IoU: 0.683
Mean IoU (test): 0.446
F1: 0.845Mean IoU: 0.7729
miou Val: 63.5Model size: 777K
mIoU: 82.5%
Top-1 IoU: 0.483Top-3 IoU: 0.712
Top-1 IoU: 0.470Top-3 IoU: 0.726
Top-1 IoU: 0.460Top-3 IoU: 0.691
Top-1 IoU: 0.488Top-3 IoU: 0.725
miou: 13.07mIoU Category: 30.42Model size: N/A
miou: 35.66mIoU Category: 58.28Model size: 3.0M
miou Val: 62.1Model size: 790K
Top-1 IoU: 0.495Top-3 IoU: 0.735
mIoU: 72.46