Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2407.15870 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917178959200256 |
|---|---|
| author | Li, Honggui Chen, Sinan Li, Dingtai Zhang, Zhengyang Hossain, Nahid Md Lokman Xu, Xinfeng Qin, Yinlu Wang, Ruobing Trocan, Maria Galayko, Dimitri Amara, Amara Sawan, Mohamad |
| author_facet | Li, Honggui Chen, Sinan Li, Dingtai Zhang, Zhengyang Hossain, Nahid Md Lokman Xu, Xinfeng Qin, Yinlu Wang, Ruobing Trocan, Maria Galayko, Dimitri Amara, Amara Sawan, Mohamad |
| contents | Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample, out-of-distribution, or out-of-domain testing images, the performance of LIC degrades significantly. Classical LIC is a serial image compression (SIC) approach that utilizes an open-loop architecture with serial encoding and decoding units. Nevertheless, according to the principles of automatic control systems, a closed-loop architecture holds the potential to improve the dynamic and static performance of LIC. Therefore, a circular image compression (CIC) approach with closed-loop encoding and decoding elements is proposed to minimize the gap between testing and training images and upgrade the capability of LIC. The proposed CIC establishes a nonlinear loop equation and proves that steady-state error between reconstructed and original images is close to zero by Taylor series expansion. The proposed CIC method possesses the property of Post-Training and Plug-and-Play which can be built on any existing advanced SIC methods. Experimental results including rate-distortion curves on five public image compression datasets demonstrate that the proposed CIC outperforms eight competing state-of-the-art open-source SIC algorithms in reconstruction capacity. Experimental results further show that the proposed method is suitable for out-of-sample testing images with dark backgrounds, sharp edges, high contrast, grid shapes, or complex patterns. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15870 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CIC: Circular Image Compression Li, Honggui Chen, Sinan Li, Dingtai Zhang, Zhengyang Hossain, Nahid Md Lokman Xu, Xinfeng Qin, Yinlu Wang, Ruobing Trocan, Maria Galayko, Dimitri Amara, Amara Sawan, Mohamad Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample, out-of-distribution, or out-of-domain testing images, the performance of LIC degrades significantly. Classical LIC is a serial image compression (SIC) approach that utilizes an open-loop architecture with serial encoding and decoding units. Nevertheless, according to the principles of automatic control systems, a closed-loop architecture holds the potential to improve the dynamic and static performance of LIC. Therefore, a circular image compression (CIC) approach with closed-loop encoding and decoding elements is proposed to minimize the gap between testing and training images and upgrade the capability of LIC. The proposed CIC establishes a nonlinear loop equation and proves that steady-state error between reconstructed and original images is close to zero by Taylor series expansion. The proposed CIC method possesses the property of Post-Training and Plug-and-Play which can be built on any existing advanced SIC methods. Experimental results including rate-distortion curves on five public image compression datasets demonstrate that the proposed CIC outperforms eight competing state-of-the-art open-source SIC algorithms in reconstruction capacity. Experimental results further show that the proposed method is suitable for out-of-sample testing images with dark backgrounds, sharp edges, high contrast, grid shapes, or complex patterns. |
| title | CIC: Circular Image Compression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.15870 |