View : 511 Download: 0
Adversarial Confidence Estimation Networks for Robust Stereo Matching
- Title
- Adversarial Confidence Estimation Networks for Robust Stereo Matching
- Authors
- Kim, Sunok; Min, Dongbo; Kim, Seungryong; Sohn, Kwanghoon
- Ewha Authors
- 민동보
- SCOPUS Author ID
- 민동보
- Issue Date
- 2021
- Journal Title
- IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
- ISSN
- 1524-9050
1558-0016
- Citation
- IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS vol. 22, no. 11, pp. 6875 - 6889
- Keywords
- Estimation; Color; Training; Feature extraction; Task analysis; Advanced driver assistance systems; Computer vision; Stereo confidence; confidence estimation; generative adversarial network; dynamic feature fusion
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Indexed
- SCIE; SCOPUS
- Document Type
- Article
- Abstract
- Stereo matching aiming to perceive the 3-D geometry of a scene facilitates numerous computer vision tasks used in advanced driver assistance systems (ADAS). Although numerous methods have been proposed for this task by leveraging deep convolutional neural networks (CNNs), stereo matching still remains an unsolved problem due to its inherent matching ambiguities. To overcome these limitations, we present a method for jointly estimating disparity and confidence from stereo image pairs through deep networks. We accomplish this through a minmax optimization to learn the generative cost aggregation networks and discriminative confidence estimation networks in an adversarial manner. Concretely, the generative cost aggregation networks are trained to accurately generate disparities at both confident and unconfident pixels from an input matching cost that are indistinguishable by the discriminative confidence estimation networks, while the discriminative confidence estimation networks are trained to distinguish the confident and unconfident disparities. In addition, to fully exploit complementary information of matching cost, disparity, and color image in confidence estimation, we present a dynamic fusion module. Experimental results show that this model outperforms the state-of-the-art methods on various benchmarks including real driving scenes.
- DOI
- 10.1109/TITS.2020.2995996
- Appears in Collections:
- 인공지능대학 > 컴퓨터공학과 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML