# Unsupervised Domain Adaptation for Depth Prediction from Images

arXiv: https://arxiv.org/abs/1909.03943 · HTML: https://mlsanity.com/paper/1909.03943/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2019.

## Built on by (most cited first, 29 of 29)

- [LocalBins: Improving Depth Estimation by Learning Local Distributions](https://mlsanity.com/paper/2203.15132/) (2022)
- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [Open Challenges in Deep Stereo: the Booster Dataset](https://mlsanity.com/paper/2206.04671/) (2022)
- [Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective](https://mlsanity.com/paper/2203.10887/) (2022)
- [NeRF-Supervised Deep Stereo](https://mlsanity.com/paper/2303.17603/) (2023)
- [Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2301.08245/) (2023)
- [DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices](https://mlsanity.com/paper/2303.13325/) (2023)
- [On the confidence of stereo matching in a deep-learning era: a quantitative evaluation](https://mlsanity.com/paper/2101.00431/) (2021)
- [Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching](https://mlsanity.com/paper/2307.16509/) (2023)
- [Neural Disparity Refinement for Arbitrary Resolution Stereo](https://mlsanity.com/paper/2110.15367/) (2021)
- [Federated Online Adaptation for Deep Stereo](https://mlsanity.com/paper/2405.14873/) (2024)
- [Physics perception in sloshing scenes with guaranteed thermodynamic consistency](https://mlsanity.com/paper/2106.13301/) (2021)
- [Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation](https://mlsanity.com/paper/2203.09737/) (2022)
- [Self-Supervised Learning of Domain Invariant Features for Depth Estimation](https://mlsanity.com/paper/2106.02594/) (2021)
- [Estimating Image Depth in the Comics Domain](https://mlsanity.com/paper/2110.03575/) (2021)
- [RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation](https://mlsanity.com/paper/2206.07047/) (2022)
- [Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions](https://mlsanity.com/paper/2210.08291/) (2022)
- [Towards Open-World Generation of Stereo Images and Unsupervised Matching](https://mlsanity.com/paper/2503.12720/) (2025)
- [UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completion](https://mlsanity.com/paper/2204.07791/) (2022)
- [UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching](https://mlsanity.com/paper/2409.02545/) (2024)
- [Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes](https://mlsanity.com/paper/2106.12958/) (2021)
- [An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo dataset](https://mlsanity.com/paper/2402.12522/) (2024)
- [MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling](https://mlsanity.com/paper/2409.02846/) (2024)
- [RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo](https://mlsanity.com/paper/2511.10107/) (2025)
- [VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction](https://mlsanity.com/paper/2608.15260/) (2026)
- [MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.10806/) (2022)
- [Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency](https://mlsanity.com/paper/2401.12019/) (2024)
- [CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching](https://mlsanity.com/paper/2504.21302/) (2025)
- [Synergistic Event-SVE Imaging for Quantitative Propellant Combustion Diagnostics](https://mlsanity.com/paper/2603.25054/) (2026)

## Abstract (arXiv)

State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop in accuracy when dealing with environments much different in appearance and/or context from those observed at training time. This domain shift issue is usually addressed by fine-tuning on smaller sets of images from the target domain annotated with depth labels. Unfortunately, relying on such supervised labeling is seldom feasible in most practical settings. Therefore, we propose an unsupervised domain adaptation technique which does not require groundtruth labels. Our method relies only on image pairs and leverages on classical stereo algorithms to produce disparity measurements alongside with confidence estimators to assess upon their reliability. We propose to fine-tune both depth-from-stereo as well as depth-from-mono architectures by a novel confidence-guided loss function that handles the measured disparities as noisy labels weighted according to the estimated confidence. Extensive experimental results based on standard datasets and evaluation protocols prove that our technique can address effectively the domain shift issue with both stereo and monocular depth prediction architectures and outperforms other state-of-the-art unsupervised loss functions that may be alternatively deployed to pursue domain adaptation.