Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching

Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching

Due to the domain differences and unbalanced disparity distribution across multiple datasets, current stereo matching approaches are commonly limited to a specific dataset and generalize poorly to others. Such domain shift issue is usually addressed by substantial adaptation on costly target-domain...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 12 vom: 17. Dez., Seite 14301-14320
1. Verfasser: Shen, Zhelun (VerfasserIn)
Weitere Verfasser: Song, Xibin, Dai, Yuchao, Zhou, Dingfu, Rao, Zhibo, Zhang, Liangjun
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM360892868
003 DE-627
005 20231226084002.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2023.3300976  |2 doi 
028 5 2 |a pubmed24n1202.xml 
035 |a (DE-627)NLM360892868 
035 |a (NLM)37590113 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Shen, Zhelun  |e verfasserin  |4 aut 
245 1 0 |a Digging Into Uncertainty-Based Pseudo-Label for Robust Stereo Matching 
264 1 |c 2023 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 07.11.2023 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Due to the domain differences and unbalanced disparity distribution across multiple datasets, current stereo matching approaches are commonly limited to a specific dataset and generalize poorly to others. Such domain shift issue is usually addressed by substantial adaptation on costly target-domain ground-truth data, which cannot be easily obtained in practical settings. In this paper, we propose to dig into uncertainty estimation for robust stereo matching. Specifically, to balance the disparity distribution, we employ a pixel-level uncertainty estimation to adaptively adjust the next stage disparity searching space, in this way driving the network progressively prune out the space of unlikely correspondences. Then, to solve the limited ground truth data, an uncertainty-based pseudo-label is proposed to adapt the pre-trained model to the new domain, where pixel-level and area-level uncertainty estimation are proposed to filter out the high-uncertainty pixels of predicted disparity maps and generate sparse while reliable pseudo-labels to align the domain gap. Experimentally, our method shows strong cross-domain, adapt, and joint generalization and obtains 1st place on the stereo task of Robust Vision Challenge 2020. Additionally, our uncertainty-based pseudo-labels can be extended to train monocular depth estimation networks in an unsupervised way and even achieves comparable performance with the supervised methods 
650 4 |a Journal Article 
700 1 |a Song, Xibin  |e verfasserin  |4 aut 
700 1 |a Dai, Yuchao  |e verfasserin  |4 aut 
700 1 |a Zhou, Dingfu  |e verfasserin  |4 aut 
700 1 |a Rao, Zhibo  |e verfasserin  |4 aut 
700 1 |a Zhang, Liangjun  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 12 vom: 17. Dez., Seite 14301-14320  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:45  |g year:2023  |g number:12  |g day:17  |g month:12  |g pages:14301-14320 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2023.3300976  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 45  |j 2023  |e 12  |b 17  |c 12  |h 14301-14320