Papers › DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate...

DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation

27 Mar 2022arXiv:2203.14211archive 2025-07-28

Zhenyu Li, Zehui Chen, Xianming Liu, Junjun Jiang

This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential for accurate depth estimation. Therefore, we propose to leverage the Transformer to model this global context with an effective attention mechanism. We also adopt an additional convolution branch to preserve the local information as the Transformer lacks the spatial inductive bias in modeling such contents. However, independent branches lead to a shortage of connections between features. To bridge this gap, we design a hierarchical aggregation and heterogeneous interaction module to enhance the Transformer features via element-wise interaction and model the affinity between the Transformer and the CNN features in a set-to-set translation manner. Due to the unbearable memory cost caused by global attention on high-resolution feature maps, we introduce the deformable scheme to reduce the complexity. Extensive experiments on the KITTI, NYU, and SUN RGB-D datasets demonstrate that our proposed model, termed DepthFormer, surpasses state-of-the-art monocular depth estimation methods with prominent margins. Notably, it achieves the most competitive result on the highly competitive KITTI depth estimation benchmark. Our codes and models are available at https://github.com/zhyever/Monocular-Depth-Estimation-Toolbox.

PaperPDFCode

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

Code

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 EstimationInductive BiasMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split DepthFormer Delta < 1.25 0.975 #28 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthFormer Delta < 1.25^2 0.997 #28 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthFormer Delta < 1.25^3 0.999 #28 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthFormer RMSE 2.143 #28 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthFormer RMSE log 0.079 #28 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthFormer Sq Rel 0.158 #28 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split DepthFormer absolute relative error 0.052 #28 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthFormer Delta < 1.25 0.921 #45 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthFormer Delta < 1.25^2 0.989 #45 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthFormer Delta < 1.25^3 0.998 #45 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthFormer RMSE 0.339 #45 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthFormer absolute relative error 0.096 #45 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DepthFormer log 10 0.041 #45 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

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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