1 code implementation • 16 Dec 2022 • Olivier Pradelle, Raphaelle Chaine, David Wendland, Julie Digne
In this paper, we show that image segmentation can benefit from 3D geometric information without requiring a 3D groundtruth, by training the geometric feature extraction and the 2D segmentation network jointly, in an end-to-end fashion, using only the 2D segmentation loss.