Self-Supervised Monocular Depth Estimation with Internal Feature Fusion
This work addresses depth estimation for autonomous driving and robotics, offering incremental improvements by adapting a semantic segmentation network.
The paper tackled monocular depth estimation by proposing DIFFNet, a novel network that integrates semantic segmentation features and attention mechanisms, achieving state-of-the-art results on the KITTI benchmark with improved performance on higher-resolution data.
Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial and semantic representations from images. Therefore, it is natural to exploit semantic segmentation networks for depth estimation. In this work, based on a well-developed semantic segmentation network HRNet, we propose a novel depth estimation network DIFFNet, which can make use of semantic information in down and upsampling procedures. By applying feature fusion and an attention mechanism, our proposed method outperforms the state-of-the-art monocular depth estimation methods on the KITTI benchmark. Our method also demonstrates greater potential on higher resolution training data. We propose an additional extended evaluation strategy by establishing a test set of challenging cases, empirically derived from the standard benchmark.