</> Code with Papers by Syntology

Papers › D-Net: A Generalised and Optimised Deep Network for Monocular Depth Estimation

D-Net: A Generalised and Optimised Deep Network for Monocular Depth Estimation

29 Sep 2021IEEE Access 2021 9archive 2025-07-28

Joshua Luke Thompson, Son Lam Phung, Abdesselam Bouzerdoum

Depth estimation is an essential component in computer vision systems for achieving 3D scene understanding. Efficient and accurate depth map estimation has numerous applications including self-driving vehicles and virtual reality tools. This paper presents a new deep network, called D-Net, for depth estimation from a single RGB image. The proposed network can be trained end-to-end, and its structure can be customised to meet different requirements in model size, speed, and prediction accuracy. Our approach gathers strong global and local contextual features at multiple resolutions, and then transfers these to high resolutions for clearer depth maps. For the encoder backbone, D-Net can utilise many state-of-the-art models including EfficientNet, HRNet and Swin Transformer to obtain dense depth maps. The proposed D-net is designed to have minimal parameters and reduced computational complexity. Extensive evaluations on the NYUv2 and KITTI benchmark datasets show that our model is highly accurate across multiple backbones, and it achieves state-of-the-art performance on both benchmarks when combined with the Swin Transformer and HRNets.

PaperPDFCode

Code

Joshuat38/D-Net pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Depth EstimationMonocular Depth EstimationScene Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split D-Net Delta < 1.25 0.963 #31 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split D-Net Delta < 1.25^2 0.995 #31 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split D-Net Delta < 1.25^3 0.999 #31 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split D-Net RMSE 2.362 #31 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split D-Net RMSE log 0.087 #31 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split D-Net Sq Rel 0.189 #31 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split D-Net absolute relative error 0.056 #31 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 D-Net Delta < 1.25 0.919 #44 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 D-Net Delta < 1.25^2 0.988 #44 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 D-Net Delta < 1.25^3 0.997 #44 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 D-Net RMSE 0.354 #44 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 D-Net absolute relative error 0.095 #44 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 D-Net log 10 0.041 #44 of 85 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections