EdgeConv with Attention Module for Monocular Depth Estimation
This addresses depth prediction for robotics and autonomous driving in challenging conditions, representing an incremental improvement with new modules.
The authors tackled monocular depth estimation by proposing a novel Patch-Wise EdgeConv Module and EdgeConv Attention Module to extract structural information from image patches, achieving state-of-the-art performance on NYU Depth V2 and KITTI Eigen split datasets.
Monocular depth estimation is an especially important task in robotics and autonomous driving, where 3D structural information is essential. However, extreme lighting conditions and complex surface objects make it difficult to predict depth in a single image. Therefore, to generate accurate depth maps, it is important for the model to learn structural information about the scene. We propose a novel Patch-Wise EdgeConv Module (PEM) and EdgeConv Attention Module (EAM) to solve the difficulty of monocular depth estimation. The proposed modules extract structural information by learning the relationship between image patches close to each other in space using edge convolution. Our method is evaluated on two popular datasets, the NYU Depth V2 and the KITTI Eigen split, achieving state-of-the-art performance. We prove that the proposed model predicts depth robustly in challenging scenes through various comparative experiments.