1st Solution Places for CVPR 2023 UG$^{\textbf{2}}$+ Challenge Track 2.1-Text Recognition through Atmospheric Turbulence
Abstract: In this technical report, we present the solution developed by our team VIELab-HUST for text recognition through atmospheric turbulence in Track 2.1 of the CVPR 2023 UG${2}$+ challenge. Our solution involves an efficient multi-stage framework that restores a high-quality image from distorted frames. Specifically, a frame selection algorithm based on sharpness is first utilized to select the sharpest set of distorted frames. Next, each frame in the selected frames is aligned to suppress geometric distortion through optical-flow-based image registration. Then, a region-based image fusion method with DT-CWT is utilized to mitigate the blur caused by the turbulence. Finally, a learning-based deartifacts method is applied to remove the artifacts in the fused image, generating a high-quality outuput. Our framework can handle both hot-air text dataset and turbulence text dataset provided in the final testing phase and achieved 1st place in text recognition accuracy. Our code will be available at https://github.com/xsqhust/Turbulence_Removal.
- Atmospheric turbulence mitigation using complex wavelet-based fusion. IEEE Transactions on Image Processing, 22(6):2398–2408, 2013.
- Towards flexible blind jpeg artifacts removal. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4997–5006, 2021.
- Region-based image fusion using complex wavelets. In Proc. 7th International Conference on Information Fusion, volume 1, pages 555–562. Citeseer, 2004.
- Pixel-and region-based image fusion with complex wavelets. Information fusion, 8(2):119–130, 2007.
- Video stabilization of atmospheric turbulence distortion. Inverse Probl. Imaging, 7(3):839–861, 2013.
- Single frame atmospheric turbulence mitigation: A benchmark study and a new physics-inspired transformer model. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIX, pages 430–446. Springer, 2022.
- An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE transactions on pattern analysis and machine intelligence, 39(11):2298–2304, 2016.
- Aster: An attentional scene text recognizer with flexible rectification. IEEE transactions on pattern analysis and machine intelligence, 41(9):2035–2048, 2018.
- Decoupled attention network for text recognition. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 12216–12224, 2020.
- Removing atmospheric turbulence via space-invariant deconvolution. IEEE transactions on pattern analysis and machine intelligence, 35(1):157–170, 2012.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.