Depth Map Decomposition for Monocular Depth Estimation
This work addresses depth estimation from single images, which is important for applications like robotics and autonomous driving, but it is incremental as it builds on existing decomposition and multi-task learning approaches.
The paper tackles monocular depth estimation by decomposing metric depth into normalized depth and scale features, using a network with shared encoder and three decoders, and achieves competitive performance with state-of-the-art methods while requiring less metric depth data for training.
We propose a novel algorithm for monocular depth estimation that decomposes a metric depth map into a normalized depth map and scale features. The proposed network is composed of a shared encoder and three decoders, called G-Net, N-Net, and M-Net, which estimate gradient maps, a normalized depth map, and a metric depth map, respectively. M-Net learns to estimate metric depths more accurately using relative depth features extracted by G-Net and N-Net. The proposed algorithm has the advantage that it can use datasets without metric depth labels to improve the performance of metric depth estimation. Experimental results on various datasets demonstrate that the proposed algorithm not only provides competitive performance to state-of-the-art algorithms but also yields acceptable results even when only a small amount of metric depth data is available for its training.