Papers › Towards Comprehensive Representation Enhancement in Semantics-guided Self-supervised...

Towards Comprehensive Representation Enhancement in Semantics-guided Self-supervised Monocular Depth Estimation

23 Oct 2022ECCV 2022 10archive 2025-07-28

Jingyuan Ma, Xiangyu Lei, Nan Liu, Xian Zhao, ShiLiang Pu

Semantics-guided self-supervised monocular depth estimation has been widely researched, owing to the strong cross-task correlation of depth and semantics. However, since depth estimation and semantic segmentation are fundamentally two types of tasks: one is regression while the other is classification, the distribution of depth feature and semantic feature are naturally different. Previous works that leverage semantic information in depth estimation mostly neglect such representational discrimination, which leads to insufficient representation enhancement of depth feature. In this work, we propose an attentionbased module to enhance task-specific feature by addressing their feature uniqueness within instances. Additionally, we propose a metric learning based approach to accomplish comprehensive enhancement on depth feature by creating a separation between instances in feature space. Extensive experiments and analysis demonstrate the effectiveness of our proposed method. In the end, our method achieves the state-of-the-art performance on KITTI dataset.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Depth EstimationMetric LearningMonocular Depth EstimationSemantic SegmentationUnsupervised Monocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split unsupervised CREMono(M + 1024x320 + Res50) Delta < 1.25 0.902 #24 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised CREMono(M + 1024x320 + Res50) Delta < 1.25^2 0.969 #24 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised CREMono(M + 1024x320 + Res50) Delta < 1.25^3 0.986 #24 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised CREMono(M + 1024x320 + Res50) RMSE 4.165 #24 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised CREMono(M + 1024x320 + Res50) RMSE log 0.171 #24 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised CREMono(M + 1024x320 + Res50) Sq Rel 0.624 #24 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised CREMono(M + 1024x320 + Res50) absolute relative error 0.099 #24 of 55 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