Papers › AdaBins: Depth Estimation using Adaptive Bins

AdaBins: Depth Estimation using Adaptive Bins

28 Nov 2020CVPR 2021 1arXiv:2011.14141archive 2025-07-28

Shariq Farooq Bhat, Ibraheem Alhashim, Peter Wonka

We address the problem of estimating a high quality dense depth map from a single RGB input image. We start out with a baseline encoder-decoder convolutional neural network architecture and pose the question of how the global processing of information can help improve overall depth estimation. To this end, we propose a transformer-based architecture block that divides the depth range into bins whose center value is estimated adaptively per image. The final depth values are estimated as linear combinations of the bin centers. We call our new building block AdaBins. Our results show a decisive improvement over the state-of-the-art on several popular depth datasets across all metrics. We also validate the effectiveness of the proposed block with an ablation study and provide the code and corresponding pre-trained weights of the new state-of-the-art model.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

shariqfarooq123/AdaBins officialmentioned in papermentioned on GitHubpytorchGPL-3.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions (arXiv:2310.15171; that paper's own run record: 62 ran (of which 0 constructed an object rather than computing a result; 44 with no instrument failure: 11 honoured, 1 violated, 32 with no contract checked; 18 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
danielzgsilva/MonoDepthAttacks mentioned on GitHubpytorchSyntology: not harvested report
dylanauty/mde-biological-vision-systems mentioned on GitHubpytorchSyntology: not harvested report
martius-lab/beta-nll mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Causal Influence Detection for Improving Efficiency in Reinforcement Learning (arXiv:2106.03443; that paper's own run record: 0 ran · 4 unverified) and On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks (arXiv:2203.09168; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-1/ms-code-16 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-224 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code8 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code5 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code6 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code6 mindsporeSyntology: not harvested report
code-implementation1/Code2 mindsporeSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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
Depth Estimation NYU-Depth V2 AdaBins RMS 0.364 #7 of 17 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split AdaBins Delta < 1.25 0.964 #35 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split AdaBins Delta < 1.25^2 0.995 #35 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split AdaBins Delta < 1.25^3 0.999 #35 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split AdaBins RMSE 2.360 #35 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split AdaBins RMSE log 0.088 #35 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split AdaBins absolute relative error 0.058 #35 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 AdaBins Delta < 1.25 0.903 #52 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 AdaBins Delta < 1.25^2 0.984 #52 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 AdaBins Delta < 1.25^3 0.997 #52 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 AdaBins RMSE 0.364 #52 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 AdaBins absolute relative error 0.103 #52 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 AdaBins log 10 0.044 #52 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

Introduced by this paper: AdaptiveBins

AdaptiveBinsAttentionEfficientNetLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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