CVPR’18 Poster “Learning 3D Shape Completion from Laser Scan Data with Weak Supervision”

This article presents the poster for our CVPR’18 paper on weakly-supervised 3D shape completion. The poster also includes improved results form our latest ArXiv pre-print. Meet us in Salt Lake City, Tuesday June 18th, to discuss.

In our CVPR'18 paper, we introduce a novel approach to 3D shape completion from sparse and noisy point clouds under weak supervision — meaning without input and ground truth pairs. On Tuesday June 18th, at CVPR'18 in Salt Lake City, we will be presenting our approach as well as results. For those not attending, the poster can be downloaded below:

Poster (∼ 6.5MB)

Figure 1 (click to enlarge): CVPR'18 poster.

What is your opinion on this article? Let me know your thoughts on Twitter @davidstutz92 or LinkedIn in/davidstutz92.