Multi-stage information diffusion for joint depth and surface normal estimation.

•We introduce a multi-stage information diffusion strategy to achieve interactions for joint-task learning through the proposed end-to-end deep neural network (MIDNet).•We design a Cross-Correlation Attention Module (CCAM) to effectively capture interactive information at different levels between depth and surface normal estimations.•Our MIDNet boasts state-of-the-art performance for joint monocular depth estimation and surface normal estimation on the NYU Depth V2 and Stanford 2D-3D-Semantic datasets, and achieves similar performance to prior art on the KITTI dataset.