Papers › TransDSSL: Transformer based Depth Estimation via Self-Supervised Learning

TransDSSL: Transformer based Depth Estimation via Self-Supervised Learning

5 Aug 2022journal 2022 8archive 2025-07-28

Daechan Han, Jeongmin Shin, Namil Kim, Soomnim Hwang, Yukyung Choi

Recently, transformers have been widely adopted for various computer vision tasks and show promising results due to their ability to encode long-range spatial dependencies in an image effectively. However, very few studies on adopting transformers in self-supervised depth estimation have been conducted. When replacing the CNN architecture with the transformer in self-supervised learning of depth, we encounter several problems such as problematic multi-scale photometric loss function when used with transformers and, insuffcient ability to capture local details. In this paper, we propose an attention-based decoder module, Pixel-Wise Skip Attention (PWSA), to enhance fine details in feature maps while keeping global context from transformers. In addition, we propose utilizing self-distillation loss with single-scale photometric loss to alleviate the instability of transformer training by using correct training signals. We demonstrate that the proposed model performs accurate predictions on large objects and thin structures that require global context and local details. Our model achieves state-ofthe-art performance among the self-supervised monocular depth estimation methods on KITTI and DDAD benchmarks

PaperPDFCode

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

DecoderDepth EstimationMonocular Depth EstimationSelf-Supervised LearningUnsupervised Monocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation DDAD TransDSSL RMSE 14.350 #4 of 4 Archive leaderboard report
Monocular Depth Estimation DDAD TransDSSL RMSE log 0.172 #4 of 4 Archive leaderboard report
Monocular Depth Estimation DDAD TransDSSL Sq Rel 3.591 #4 of 4 Archive leaderboard report
Monocular Depth Estimation DDAD TransDSSL absolute relative error 0.151 #4 of 4 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL Delta < 1.25 0.906 #14 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL Delta < 1.25^2 0.967 #14 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL Delta < 1.25^3 0.984 #14 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL Mono O #14 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL RMSE 4.321 #14 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL RMSE log 0.172 #14 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL Sq Rel 0.711 #14 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised TransDSSL absolute relative error 0.095 #14 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