Unsupervised Deep Event Stereo for Depth Estimation
- Authors
- Uddin, S. M. Nadim; Ahmed, Soikat Hasan; Jung, Yong Ju
- Issue Date
- Nov-2022
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Cameras; Estimation; Image matching; Correlation; Training; Lighting; Image reconstruction; Event camera; stereo matching; depth estimation; unsupervised deep learning
- Citation
- IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, v.32, no.11, pp.7489 - 7504
- Journal Title
- IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
- Volume
- 32
- Number
- 11
- Start Page
- 7489
- End Page
- 7504
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/86388
- DOI
- 10.1109/TCSVT.2022.3189480
- ISSN
- 1051-8215
- Abstract
- Bio-inspired event cameras have been considered effective alternatives to traditional frame-based cameras for stereo depth estimation, especially in challenging conditions such as low-light or high-speed environments. Recently, deep learning-based supervised event stereo matching methods have achieved significant performance improvements over the traditional event stereo methods. However, the supervised methods depend on ground-truth disparity maps for training, and it is difficult to secure a large amount of ground-truth disparity maps. A feasible alternative is to devise an unsupervised event stereo method that can be trained without ground-truth disparity maps. To this end, we propose the first unsupervised event stereo matching method that can predict dense disparity maps, and is trained by transforming the depth estimation problem into a warping-based reconstruction problem. We propose a novel unsupervised loss function that enforces the network to minimize the feature-level epipolar correlation difference between the ground-truth intensity images and warped images. Moreover, we propose a novel event embedding mechanism that utilizes both temporal and spatial neighboring events to capture spatio-temporal relationships among the events for stereo matching. Experimental results reveal that the proposed method outperforms the baseline unsupervised methods by significant margins (e.g., up to 16.88% improvement) and achieves comparable results with the existing supervised methods. Extensive ablation studies validate the efficacy of the proposed modules and architectural choices.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 소프트웨어학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/86388)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.