AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach

被引:9
|
作者
Song, Xiao [1 ]
Yang, Guorun [2 ]
Zhu, Xinge [3 ]
Zhou, Hui [1 ]
Ma, Yuexin [4 ]
Wang, Zhe [1 ]
Shi, Jianping [1 ]
机构
[1] SenseTime Grp Ltd, Hong Kong, Peoples R China
[2] Chinese Acad Sci, Shenzhen Inst Adv Technol, Beijing, Peoples R China
[3] Chinese Univ Hong Kong, Hong Kong, Peoples R China
[4] ShanghaiTech Univ, Shanghai, Peoples R China
关键词
Domain adaptation; Stereo matching; Non-adversarial progressive color transfer; Cost normalization; Self-supervised occlusion-aware reconstruction;
D O I
10.1007/s11263-021-01549-6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, records on stereo matching benchmarks are constantly broken by end-to-end disparity networks. However, the domain adaptation ability of these deep models is quite limited. Addressing such problem, we present a novel domain-adaptive approach called AdaStereo that aims to align multi-level representations for deep stereo matching networks. Compared to previous methods, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline. Firstly, we propose a non-adversarial progressive color transfer algorithm for input image-level alignment. Secondly, we design an efficient parameter-free cost normalization layer for internal feature-level alignment. Lastly, a highly related auxiliary task, self-supervised occlusion-aware reconstruction is presented to narrow the gaps in output space. We perform intensive ablation studies and break-down comparisons to validate the effectiveness of each proposed module. With no extra inference overhead and only a slight increase in training complexity, our AdaStereo models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo, even outperforming some state-of-the-art disparity networks finetuned with target-domain ground-truths. Moreover, based on two additional evaluation metrics, the superiority of our domain-adaptive stereo matching pipeline is further uncovered from more perspectives. Finally, we demonstrate that our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments.
引用
收藏
页码:226 / 245
页数:20
相关论文
共 50 条
  • [21] Automatic Domain-Adaptive Sentiment Analysis with SentiMap
    Veltmeijer, Emmeke
    Gerritsen, Charlotte
    [J]. INTERNATIONAL JOURNAL OF SEMANTIC COMPUTING, 2024, 18 (01) : 97 - 120
  • [22] How to Learn a Domain-Adaptive Event Simulator?
    Gu, Daxin
    Li, Jia
    Zhang, Yu
    Tian, Yonghong
    [J]. PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 1275 - 1283
  • [23] DOMAIN-ADAPTIVE PEDESTRIAN DETECTION IN THERMAL IMAGES
    Guo, Tiantong
    Cong Phuoc Huynh
    Solh, Mashhour
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 1660 - 1664
  • [24] Domain-Adaptive Neural Automated Essay Scoring
    Cao, Yue
    Jin, Hanqi
    Wan, Xiaojun
    Yu, Zhiwei
    [J]. PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20), 2020, : 1011 - 1020
  • [25] A LOCAL STEREO MATCHING APPROACH USING ADAPTIVE WEIGHT BOUNDARY
    Zhu, Kongfen
    Zhang, Xiong
    [J]. 2015 IEEE CHINA SUMMIT & INTERNATIONAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING, 2015, : 235 - 239
  • [26] EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation
    Saha, Suman
    Hoyer, Lukas
    Obukhov, Anton
    Dai, Dengxin
    Van Gool, Luc
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 19177 - 19188
  • [27] Domain-Adaptive Pretraining Methods for Dialogue Understanding
    Wu, Han
    Xu, Kun
    Song, Linfeng
    Jin, Lifeng
    Zhang, Haisong
    Song, Linqi
    [J]. ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2, 2021, : 665 - 669
  • [28] Domain-Adaptive Few-Shot Learning
    Zhao, An
    Ding, Mingyu
    Lu, Zhiwu
    Xiang, Tao
    Niu, Yulei
    Guan, Jiechao
    Wen, Ji-Rong
    [J]. 2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, : 1389 - 1398
  • [29] Adaptive Spatial Sparsification for Efficient Multi-View Stereo Matching
    Zhou, Xiao-Qing
    Wang, Xiang
    Zheng, Jin
    Bai, Xiao
    [J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2023, 51 (11): : 3079 - 3091
  • [30] Neural adaptive stereo matching
    Binaghi, E
    Gallo, I
    Marino, G
    Raspanti, M
    [J]. PATTERN RECOGNITION LETTERS, 2004, 25 (15) : 1743 - 1758