Papers › Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals

Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals

8 Jan 2021archive 2025-07-28

Minsoo Song, Seokjae Lim, Wonjun Kim

With a great success of the generative model via deep neural networks, monocular depth estimation has been actively studied by exploiting various encoder-decoder architectures. However, the decoding process in most previous methods, which repeats simple up-sampling operations, probably fails to fully utilize underlying properties of well-encoded features for monocular depth estimation. To resolve this problem, we propose a simple but effective scheme by incorporating the Laplacian pyramid into the decoder architecture. Specifically, encoded features are fed into different streams for decoding depth residuals, which are defined by decomposition of the Laplacian pyramid, and corresponding outputs are progressively combined to reconstruct the final depth map from coarse to fine scales. This is fairly desirable to precisely estimate the depth boundary as well as the global layout. We also propose to apply weight standardization to pre-activation convolution blocks of the decoder architecture, which gives a great help to improve the flow of gradients and thus makes optimization easier. Experimental results on benchmark datasets constructed under various indoor and outdoor environments demonstrate that the proposed method is effective for monocular depth estimation compared to state-of-the-art models. The code and model are publicly available at: https://github.com/tjqansthd/LapDepth-release.

PaperPDFCode

Code

tjqansthd/LapDepth-release mentioned in paperpytorch 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

DecoderDepth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split LapDepth Delta < 1.25 0.962 #37 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split LapDepth Delta < 1.25^2 0.994 #37 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split LapDepth Delta < 1.25^3 0.999 #37 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split LapDepth RMSE 2.446 #37 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split LapDepth RMSE log 0.091 #37 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split LapDepth absolute relative error 0.059 #37 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LapDepth Delta < 1.25 0.895 #55 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LapDepth Delta < 1.25^2 0.983 #55 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LapDepth Delta < 1.25^3 0.996 #55 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LapDepth RMSE 0.384 #55 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LapDepth absolute relative error 0.105 #55 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LapDepth log 10 0.045 #55 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.

Methods

ConvolutionLaplacian PyramidReLUResNeXtResidual ConnectionWeight Standardization

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