Jiaqi Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiaqi Tang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Fugee Tsung
The Hong Kong University of Science and Technology, Hong Kong
1 shared publication - Hao Lu
Information Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
1 shared publication - Ming Ge
Hong Kong Productivity Council
1 shared publication Ruizheng Wu
SmartMore Corporation
1 shared publication- Ruizheng Wu
SmartMore Corporation
1 shared publication Sixing Hu
SmartMore Corporation
1 shared publication
Latest Publications
- 26 October 2024
- Published by Springer Nature
- p. 307-324
An Incremental Unified Framework for Small Defect Inspection
- 26 October 2024
- Published by Springer Nature
- p. 307-324
An Incremental Unified Framework for Small Defect Inspection
- Open Access
Learning to Remove Wrinkled Transparent Film with Polarized Prior
In this paper, we study a new problem, Film Removal (FR), which attempts to remove the interference of wrinkled transparent films and reconstruct the original information under films for industrial recognition systems. We first physically model the imaging of industrial materials covered by the film. Considering the specular highlight from the film can be effectively recorded by the polarized camera, we build a practical dataset with polarization information containing paired data with and without transparent film. We aim to remove interference from the film (specular highlights and other degradations) with an end-to-end framework. To locate the specular highlight, we use an angle estimation network to optimize the polarization angle with the minimized specular highlight. The image with minimized specular highlight is set as a prior for supporting the reconstruction network. Based on the prior and the polarized images, the reconstruction network can decouple all degradations from the film. Extensive experiments show that our framework achieves SOTA performance in both image reconstruction and industrial downstream tasks. Our code will be released at \url{https://github.com/jqtangust/FilmRemoval}.
Open AccessLearning to Remove Wrinkled Transparent Film with Polarized Prior
In this paper, we study a new problem, Film Removal (FR), which attempts to remove the interference of wrinkled transparent films and reconstruct the original information under films for industrial recognition systems. We first physically model the imaging of industrial materials covered by the film. Considering the specular highlight from the film can be effectively recorded by the polarized camera, we build a practical dataset with polarization information containing paired data with and without transparent film. We aim to remove interference from the film (specular highlights and other degradations) with an end-to-end framework. To locate the specular highlight, we use an angle estimation network to optimize the polarization angle with the minimized specular highlight. The image with minimized specular highlight is set as a prior for supporting the reconstruction network. Based on the prior and the polarized images, the reconstruction network can decouple all degradations from the film. Extensive experiments show that our framework achieves SOTA performance in both image reconstruction and industrial downstream tasks. Our code will be released at \url{https://github.com/jqtangust/FilmRemoval}.