test mIoU: 70.8%val mIoU: 74.2%
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
test mIoU: 72.9%val mIoU: 69.3%
mIOU: 51.3
test mIoU: 68.9%val mIoU: 64.3%
test mIoU: 74.4%val mIoU: 69.0%
test mIoU: 73.3%val mIoU: 68.7%
test mIoU: 65.4%
mIOU: 53.73
test mIoU: 63.1%
test mIoU: 75.6%val mIoU: 70.2%
mIoU: 75.8mAcc: 84.5Model Size: 19.7M
test mIoU: 61.6%
mIOU: 47.64
test mIoU: 72.6%val mIoU: 70.3%
test mIoU: 75.5%val mIoU: 72.3%
test mIoU: 71.2%
mIoU: 58.4Overall Accuracy: 97.2Model size: N/A
mIOU: 53.2
mIOU: 15.92
mIoU: 70.6mAcc: 79.7Model Size: 41.5M
mIoU: 76.5mAcc: 84.1Model Size: 24.1M
test mIoU: 73.3%val mIoU: 67.6%
mIOU: 50.65
test mIoU: 66.4%val mIoU: 64.7%
mIoU: 57.4Overall Accuracy: 96.4Model size: N/A
test mIoU: 66.0%
test mIoU: 74.8%val mIoU: 67.8%
test mIoU: 63.1%
test mIoU: 75.2%val mIoU: 71.3%
test mIoU: 70.8%val mIoU: 68.0%