Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data

Nikolay Patakin, Anna Vorontsova, Mikhail Artemyev, Anton Konushin 0002. Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. pages 1695-1704, IEEE, 2022. [doi]

Abstract

Abstract is missing.