# DESC: Domain Adaptation for Depth Estimation via Semantic Consistency

arXiv: https://arxiv.org/abs/2009.01579 · HTML: https://mlsanity.com/paper/2009.01579/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2020.

## Built on by (most cited first, 25 of 25)

- [Unsupervised Domain Generalization by Learning a Bridge Across Domains](https://mlsanity.com/paper/2112.02300/) (2021)
- [A Unified Framework for Domain Adaptive Pose Estimation](https://mlsanity.com/paper/2204.00172/) (2022)
- [CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation](https://mlsanity.com/paper/2303.10147/) (2023)
- [PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation](https://mlsanity.com/paper/2406.06679/) (2024)
- [A Survey on RGB-D Datasets](https://mlsanity.com/paper/2201.05761/) (2022)
- [Self-Supervised Learning of Domain Invariant Features for Depth Estimation](https://mlsanity.com/paper/2106.02594/) (2021)
- [Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation](https://mlsanity.com/paper/2208.00160/) (2022)
- [SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery](https://mlsanity.com/paper/2406.18151/) (2024)
- [CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters](https://mlsanity.com/paper/2110.14347/) (2021)
- [Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer](https://mlsanity.com/paper/2208.12527/) (2022)
- [AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach](https://mlsanity.com/paper/2112.04974/) (2021)
- [3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling](https://mlsanity.com/paper/2209.09231/) (2022)
- [Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation](https://mlsanity.com/paper/2303.05164/) (2023)
- [PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation](https://mlsanity.com/paper/2501.01121/) (2025)
- [Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems](https://mlsanity.com/paper/2204.10384/) (2022)
- [Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss](https://mlsanity.com/paper/2103.05902/) (2021)
- [GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embedding](https://mlsanity.com/paper/2312.06021/) (2023)
- [Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation](https://mlsanity.com/paper/2410.06982/) (2024)
- [Calibrating Panoramic Depth Estimation for Practical Localization and Mapping](https://mlsanity.com/paper/2308.14005/) (2023)
- [Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation](https://mlsanity.com/paper/2405.17704/) (2024)
- [Domain Adaptive Monocular Depth Estimation With Semantic Information](https://mlsanity.com/paper/2104.05764/) (2021)
- [Domain-Transferred Synthetic Data Generation for Improving Monocular Depth Estimation](https://mlsanity.com/paper/2405.01113/) (2024)
- [Towards Conditional Feature Alignment for Cross-Domain Counting](https://mlsanity.com/paper/2506.17137/) (2025)
- [FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment](https://mlsanity.com/paper/2506.22509/) (2025)
- [RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes](https://mlsanity.com/paper/2602.09532/) (2026)

## Abstract (arXiv)

Accurate real depth annotations are difficult to acquire, needing the use of special devices such as a LiDAR sensor. Self-supervised methods try to overcome this problem by processing video or stereo sequences, which may not always be available. Instead, in this paper, we propose a domain adaptation approach to train a monocular depth estimation model using a fully-annotated source dataset and a non-annotated target dataset. We bridge the domain gap by leveraging semantic predictions and low-level edge features to provide guidance for the target domain. We enforce consistency between the main model and a second model trained with semantic segmentation and edge maps, and introduce priors in the form of instance heights. Our approach is evaluated on standard domain adaptation benchmarks for monocular depth estimation and show consistent improvement upon the state-of-the-art.