Special Issue description
IEEE Transactions on Pattern Analysis and Machine Intelligence Special Issue:
Image and Video Inpainting and Denoising
Inpainting is the field of research devoted to the development of methods to replace missing or corrupted parts of the image data, where often, only small regions of the image are affected. This problem has been widely studied within Computer Vision and Pattern Recognition. The interest of this community mainly raises from the number of problems/tasks that would be benefited from solving this problem. Most notably, an idea inpainting method could get rid of the occlusion problem, which is present in almost all real world applications of scene understanding. The problem has been approached with a wide diversity of techniques. The first methods that thrived at reconstructing a texture or at repeating pattern either by using the structure of the textures [1, 2, 3] or by using patches ,
sometimes also called image quilting. As in other subfields, recent advances in computer vision, partially led by Convolutional Neural Networks (CNNs)  have shown that these models are capable of learning a great amount of semantic information, useful in tasks such as classification or segmentation. There have also been advances in reconstructing missing information and denoising by using denoising autoencoders . The work of  is capable of extracting relevant features and reconstruct missing information based on them. More recently there have been considerable advances in generative models with Generative Adversarial Networks (GANs) . For the problem of semantic inpainting this does not only provide yields a good generative model, but also a way to qualify some
qualities of the results that traditional measures were not able to measure accurately.
The recent and successful efforts for dealing with the inpainting and denoising problems put us in a perfect time to capture a snapshot of the state of the art at the early years of the deep learning era. With deep-learning-based solutions dominating this task, with the recent release of associated benchmarks and with the organization of relevant workshops in top venues, a special issue in the topic would be an invaluable compilation that will pave the way for the development of the area in the forthcoming years. Accordingly, we are proposing a special issue in Transactions on Pattern Analysis and Machine Intelligence devoted to cover all aspects of image and video inpainting and denoising. The special issue aims to compile articles providing an historical review of the field, contributions reporting the
latest advances in this research topic, and articles providing a perspective on the open problems and challenges associated to image inpainting and denoising. The special issue is associated to a couple of competitions and their respective workshops collocated with WCCI 2018 and ECCV 2018. The workshops scopes are totally aligned with the topic of the proposed special issue (see below); besides, the associated competitions deal with the problems of pose estimation in occluded images, video de-captioning, and inpainting and denoising for fingerprint verification. We expect a crowded participation in both, challenges and workshops. The authors of best papers presented at the workshops and top ranking participants in the challenges will be invited to submit extended/improved versions of their work. Besides with the open Call for Papers for this special issue on all aspects of image and video inpainting and denoising we expect to define the current referent works in the field as well as to push its state of the art.
Topics of Interest
Advances in all aspects of computer vision and pattern recognition devoted to image and video inpainting. The proposed SI will focus on all aspects related to inpainting and denoising from videos and still images. More specifically, the committee encourages the submission of papers making fundamental or practical contributions to inpaining (or denoising) in connection with various computer vision topics including, but is not limited to:
- Generative Adversarial Networks for image/video inpainting and denoising,
- Pose estimation recovery from images/video with missing or occluded information,
- Video de-captioning,
- Inpainting/denoising for latent fingerprint recognition,
- Unsupervised learning in image/video inpainting,
- Future frame video prediction,
- Structural image/video inpainting,
- Textural image/video inpainting,
- Combined structural and textural inpainting,
- Multimodal image/video inpainting (i.e., RGB-D)
 Alexei A Efros and Thomas K Leung. Texture synthesis by non-parametric sampling. In:
Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on. Vol. 2.
IEEE. 1999, pp. 1033-1038.
 Alexei A Efros and William T Freeman. Image quilting for texture synthesis and transfer. In:
Proceedings of the 28th annual conference on Computer graphics and interactive techniques. ACM.
2001, pp. 341-346
 David J Heeger and James R Bergen. Pyramid-based texture analysis synthesis. In: Proceedings
of the 22nd annual conference on Computer graphics and interactive techniques. ACM. 1995, pp. 229-
 Lin Liang et al. Real-time texture synthesis by patch-based sampling. In: ACM Transactions on
Graphics (ToG) 20.3 (2001), pp. 127-150.
 Alex Krizhevsky, Ilya Sutskever, and Georey E Hinton. Imagenet classication with deep
convolutional neural networks. In: Advances in neural information processing systems. 2012, pp. 1097-
 Pascal Vincent et al. Stacked denoising autoencoders: Learning useful representations in a deep
network with a local denoising criterion". In: Journal of Machine Learning Research 11.Dec (2010),
 Ian Goodfellow et al. Generative adversarial nets. In: Advances in neural information
processing systems. 2014, pp. 2672-2680.