Skip to search formSkip to main contentSkip to account menu
- Corpus ID: 270067917
@inproceedings{ElGhoussani2024ConsistencyRF, title={Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation}, author={Amir El-Ghoussani and Julia Hornauer and Gustavo Carneiro and Vasileios Belagiannis}, year={2024}, url={https://api.semanticscholar.org/CorpusID:270067917}}
- Amir El-Ghoussani, Julia Hornauer, Vasileios Belagiannis
- Published 27 May 2024
- Computer Science
This work forms unsupervised domain adaptation for monocular depth estimation as a consistency-based semi-supervised learning problem by assuming access only to the source domain ground truth labels and introduces a pairwise loss function that regularises predictions on the source domain while enforcing perturbation consistency.
Figures and Tables from this paper
- figure 1
- table 1
- figure 2
- table 2
- figure 3
- table 3
- figure 4
- table 4
- table 5
- figure 5
- table 6
- figure 6
- table 7
- figure 7
- table 8
- figure 8
- table 9
- table 10
Ask This Paper
BETA
AI-Powered
Ask This Paper
BETA
AI-Powered
Unknown Error
An unexpected error occurred. Please try again.
No Answer Found
Ask another question that can be answered by this paper or rephrase your question.
We are still processing this paper
Please try again later.
Question Answering Unavailable
Please try again later.
No Response
The server took too long to answer your question. You can either rephrase your question or wait until it is less busy.
AI-Generated
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Thank you for your feedback!
We're sorry, something went wrong while submitting this feedback.
Supporting Statements
Our system tries to constrain to information found in this paper. Results quality may vary. Learn more about how we generate these answers.
Feedback?
54 References
- Adrian Lopez-RodriguezK. Mikolajczyk
- 2022
Computer Science, Engineering
International Journal of Computer Vision
This paper proposes a domain adaptation approach to train a monocular depth estimation model using a fully-annotated source dataset and a non-annotation target dataset, and bridges the domain gap by leveraging semantic predictions and low-level edge features to provide guidance for the target domain.
- 30
- PDF
- Shanshan ZhaoHuan FuMingming GongD. Tao
- 2019
Computer Science, Engineering
2019 IEEE/CVF Conference on Computer Vision and…
This work proposes a geometry-aware symmetric domain adaptation framework (GASDA) to explore the labels in the synthetic data and epipolar geometry in the real data jointly and achieves better image style transfer and generates high-quality depth maps.
- 153
- Highly Influential[PDF]
- Jogendra Nath KunduP. UppalaAnuj PahujaR. Venkatesh Babu
- 2018
Computer Science, Engineering
2018 IEEE/CVF Conference on Computer Vision and…
The proposed AdaDepth - an unsupervised domain adaptation strategy for the pixel-wise regression task of monocular depth estimation performs competitively with other established approaches on depth estimation tasks and achieves state-of-the-art results in a semi-supervised setting.
- 171
- Highly Influential[PDF]
- Clément GodardOisin Mac AodhaG. Brostow
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
This paper proposes a novel training objective that enables the convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data, and produces state of the art results for monocular depth estimation on the KITTI driving dataset.
- 2,585 [PDF]
- Yu-Ting YenChia-Ni LuWei-Chen ChiuYi-Hsuan Tsai
- 2022
Computer Science
ECCV
This paper develops a domain adaptation framework via generating reliable pseudo ground truths of depth from real data to provide direct supervisions and proposes two mechanisms for pseudo-labeling, which improve depth estimation in various settings.
- 6
- Highly Influential[PDF]
- Yevhen KuznietsovJ. StücklerB. Leibe
- 2017
Computer Science, Engineering
2017 IEEE Conference on Computer Vision and…
This paper proposes a novel approach to depth map prediction from monocular images that learns in a semi-supervised way and uses sparse ground-truth depth for supervised learning, and also enforces the deep network to produce photoconsistent dense depth maps in a stereo setup using a direct image alignment loss.
- 630 [PDF]
- Amir Atapour-AbarghoueiT. Breckon
- 2018
Computer Science, Engineering
2018 IEEE/CVF Conference on Computer Vision and…
This work takes advantage of style transfer and adversarial training to predict pixel perfect depth from a single real-world color image based on training over a large corpus of synthetic environment data.
- 257
- PDF
- Iro LainaC. RupprechtVasileios BelagiannisFederico TombariNassir Navab
- 2016
Computer Science
2016 Fourth International Conference on 3D Vision…
A fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and depth maps is proposed and a novel way to efficiently learn feature map up-sampling within the network is presented.
- 1,673 [PDF]
- Julia HornauerVasileios Belagiannis
- 2022
Computer Science, Engineering
ECCV
This work proposes a post hoc uncertainty estimation approach for an already trained and thus fixed depth estimation model, represented by a deep neural network, that achieves state-of-the-art uncertainty estimation results on the KITTI and NYU Depth V2 benchmarks without the need to retrain the neural network.
- 20 [PDF]
- A. AmiriS. LooHong Zhang
- 2019
Computer Science, Engineering
2019 IEEE International Conference on Robotics…
This paper presents research in single-image depth prediction using semi-supervised training that outperforms the state-of-the-art, and describes the correct use of ground truth depth derived from LiDAR that can significantly reduce prediction error.
- 53 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers