DESC: Domain Adaptation for Depth Estimation via Semantic Consistency

2020-09-03 · Adrian Lopez-Rodriguez, Krystian Mikolajczyk

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.

📄 PDF Abstract BibTeX arXiv:2009.01579

Code (0)

등록된 구현이 없습니다.

Tasks

Depth Estimation Domain Adaptation Monocular Depth Estimation Semantic Segmentation

Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

2021-04-28 · ICCV 2021 10 · Qin Wang, Dengxin Dai, Lukas Hoyer, Luc van Gool 외

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth e…

Depth Estimation Depth Prediction Domain Adaptation Feature Correlation+3

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

2021-03-30 · ICCV 2021 10 · Vitor Guizilini, Jie Li, Rares Ambrus, Adrien Gaidon

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world…

Depth Estimation Depth Prediction Domain Adaptation Monocular Depth Estimation+3

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation

2021-05-17 · CVPR 2021 1 · Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis 외

We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be compleme…

Depth Estimation Domain Adaptation Monocular Depth Estimation Multi-Task Learning+4

Geometry-Aware Network for Domain Adaptive Semantic Segmentation

2022-12-02 · Yinghong Liao, Wending Zhou, Xu Yan, Shuguang Cui 외

Measuring and alleviating the discrepancies between the synthetic (source) and real scene (target) data is the core issue for domain adaptive semantic segmentation. Though recent works have introduced depth information i…

Depth Estimation Depth Prediction Disentanglement Domain Adaptation+2

A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment

2022-09-13 · IEEE Access 2022 9 · Kieu Dang Nam, Nguyen Minh Tu, Trinh Van Dieu, Muriel Visani 외

Domain adaptation methods in machine learning deal with the domain shift issue by aligning source and target data representation. This paper proposes a novel domain adaptation method for semantic segmentation that exploi…

Depth Estimation Domain Adaptation Segmentation Semantic Segmentation+2