Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information

no code implementations • 18 Nov 2022 • Ahmed Ben Saad, Kristina Prokopetc, Josselin Kherroubi, Axel Davy, Adrien Courtois, Gabriele Facciolo

In this paper we will focus on the depth information, which can be obtained by using a depth estimation network or measured from available data (stereovision, parallax motion, LiDAR, etc.).

Contrastive Learning Depth Estimation +2