Unsupervised Domain Adaptation for Depth Prediction from Images

被引:49
|
作者
Tonioni, Alessio [1 ]
Poggi, Matteo [1 ]
Mattoccia, Stefano [1 ]
Di Stefano, Luigi [1 ]
机构
[1] Univ Bologna, Dept Comp Sci & Engn, BO-40126 Bologna, Italy
关键词
Training; Reliability; Estimation; Loss measurement; Computer architecture; Prediction algorithms; Deep learning; depth estimation; unsupervised learning; self-supervised learning; domain adaptation; COST AGGREGATION; STEREO; ACCURATE;
D O I
10.1109/TPAMI.2019.2940948
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:2396 / 2409
页数:14
相关论文
共 50 条
  • [1] Depth Guidance Unsupervised Domain Adaptation for Semantic Segmentation
    Lu J.
    Shi J.
    Zhu H.
    Sun Y.
    Cheng Z.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2024, 36 (01): : 133 - 141
  • [2] Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
    Saha, Suman
    Obukhov, Anton
    Paudel, Danda Pani
    Kanakis, Menelaos
    Chen, Yuhua
    Georgoulis, Stamatios
    Van Gool, Luc
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 8193 - 8203
  • [3] Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection
    Scheck, Tobias
    Grassi, Ana Perez
    Hirtz, Gangolf
    VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP, 2021, : 319 - 327
  • [4] Unsupervised Domain Adaptation of Deep Networks for ToF Depth Refinement
    Agresti, Gianluca
    Schaefer, Henrik
    Sartor, Piergiorgio
    Incesu, Yalcin
    Zanuttigh, Pietro
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) : 9195 - 9208
  • [5] Unsupervised Domain Adaptation for Semantic Segmentation using Depth Distribution
    Wu, Quanliang
    Liu, Huajun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [6] Unsupervised Depth and Confidence Prediction from Monocular Images using Bayesian Inference
    Bhutani, Vishal
    Vankadart, Madhu
    Jha, Omprakash
    Majumder, Anima
    Kumar, Swagat
    Dutta, Samrat
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 10108 - 10115
  • [7] Unsupervised Deep Domain Adaptation for Heterogeneous Defect Prediction
    Gong, Lina
    Jiang, Shujuan
    Yu, Qiao
    Jiang, Li
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2019, E102D (03) : 537 - 549
  • [8] Noise Transfer for Unsupervised Domain Adaptation of Retinal OCT Images
    Koch, Valentin
    Holmberg, Olle
    Spitzer, Hannah
    Schiefelbein, Johannes
    Asani, Ben
    Hafner, Michael
    Theis, Fabian J.
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT II, 2022, 13432 : 699 - 708
  • [9] Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images
    Bermuedez-Chacon, Roger
    Altingoevde, Okan
    Becker, Carlos
    Salzmann, Mathieu
    Fua, Pascal
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2020, 39 (04) : 1256 - 1267
  • [10] RESTORATION OF CATARACT FUNDUS IMAGES VIA UNSUPERVISED DOMAIN ADAPTATION
    Li, Heng
    Liu, Haofeng
    Hu, Yan
    Higashita, Risa
    Zhao, Yitian
    Qi, Hong
    Liu, Jiang
    2021 IEEE 18TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2021, : 516 - 520