Controllable Image Processing via Adaptive FilterBank Pyramid
| العنوان: | Controllable Image Processing via Adaptive FilterBank Pyramid |
|---|---|
| المؤلفون: | Lu Yuan, Gang Hua, Dongdong Chen, Qingnan Fan, Angelica I. Aviles-Rivero, Nenghai Yu, Jing Liao |
| المصدر: | IEEE Transactions on Image Processing. 29:8043-8054 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Deblocking filter, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image processing, 02 engineering and technology, Filter bank, Computer Graphics and Computer-Aided Design, Convolutional neural network, Convolution, Operator (computer programming), Feature (computer vision), Computer Science::Computer Vision and Pattern Recognition, Pyramid, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Pyramid (image processing), Algorithm, Software, Image restoration, Smoothing |
| الوصف: | Traditional image processing operators often provide some control parameters to tweak the final results. Recently, different convolutional neural networks have been used to approximate or improve these operators. However, in those methods, one single model can only handle one operator of a specific parameter value and does not support parameter tuning. In this paper, we propose a new plugin module, “Adaptive Filterbank Pyramid” , which can be inserted into a backbone network to support multiple operators and continuous parameter tuning. Our module explicitly represents one operator with one filterbank pyramid. To generate the results of a specific operator, the corresponding filterbank pyramid is convolved with the intermediate feature pyramid produced by the backbone network. The weights of the filterbank pyramid are directly regressed by another sub-network, which is jointly trained with the backbone network and adapted to the input parameter, thus enabling continuous parameter tuning. We applied the proposed module for a large variety of image processing tasks, including image smoothing, image denoising, image deblocking, image enhancement and neural style transfer. Experiments show that our method is generalized to different types of image processing tasks and different backbone network structures. Compared to the single-operator-single-parameter baseline, our method can produce comparable results but is significantly more efficient in both training and testing. |
| تدمد: | 1941-0042 1057-7149 |
| DOI: | 10.1109/tip.2020.3009844 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::9a959c775eb6c29f65f5b921836c6d5e https://doi.org/10.1109/tip.2020.3009844 |
| Rights: | CLOSED |
| رقم الانضمام: | edsair.doi...........9a959c775eb6c29f65f5b921836c6d5e |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 19410042 10577149 |
|---|---|
| DOI: | 10.1109/tip.2020.3009844 |