Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 30, Issue -, Pages 205-209Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2023.3251921
Keywords
Laplace equations; Image resolution; Estimation; Image reconstruction; Fuses; Refining; Layout; Depth refinement; Laplacian pyramid fusion; multi-scale residual
Categories
Ask authors/readers for more resources
Deep learning approach has achieved great success in monocular depth estimation. However, the learned deep network may produce a depth map with fewer details and incorrect global depth layout, especially when the learned network is applied to a high-resolution image. Our proposed multi-scale residual Laplacian pyramid fusion net (MS-RLap-FNet) aims to generate a high-quality depth map by refining the depth maps estimated by existing models.
Deep learning approach has achieved great success in monocular depth estimation. However, the learned deep network may produce a depth map with fewer details and incorrect global depth layout, especially when the learned network is applied to a high-resolution image. In order to generate a high-quality depth map with better global structure and richer details, we propose a multi-scale residual Laplacian pyramid fusion net (MS-RLap-FNet), to fuse the multi-scale depth maps estimated by the existing depth estimation models, for depth refinement. Our approach relies on a proposed multi-scale residual Laplacian pyramid decomposition of the multi-scale depth maps, and the fusion network modules to gradually refine the depth maps based on the decomposition from low to high resolution. Comprehensive experiments show that our method, by refining the depth maps based on three popular monocular depth estimation models (DPT, MiDas, SGR), outperforms the existing state-of-the-art methods both in quantity and quality on three public datasets with different image resolutions. The depth map refined by our method has better global depth layout with richer fine details.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available