DPNet: Detail-preserving network for high quality monocular depth estimation

Abstract

Existing monocular depth estimation methods are unsatisfactory due to the inaccurate inference of depth details and the loss of spatial information. In this paper, we present a novel detail-preserving network (DPNet), i.e., a dual-branch network architecture that fully addresses the above problems and facilitates the depth map inference. Specifically, in contextual branch (CB), we propose an effective and efficient nonlocal spatial attention module by introducing non-local filtering strategy to explicitly exploit the pixel relationship in spatial domain, which can bring significant promotion on depth details inference. Meanwhile, we design a spatial branch (SB) to preserve the spatial information and generate high-resolution features from input color image. A refinement module (RM) is then proposed to fuse the heterogeneous features from both spatial and contextual branches to obtain a high quality depth map. Experimental results show that the proposed method outperforms SOTA methods on benchmark RGB-D datasets.