Abstract
AbstractDiffusion-based inpainting can reconstruct missing image areas with high quality from sparse data, provided that their location and their values are well optimised. This is particularly useful for applications such as image compression, where the original image is known. Selecting the known data constitutes a challenging optimisation problem, that has so far been only investigated with model-based approaches. So far, these methods require a choice between either high quality or high speed since qualitatively convincing algorithms rely on many time-consuming inpaintings. We propose the first neural network architecture that allows fast optimisation of pixel positions and pixel values for homogeneous diffusion inpainting. During training, we combine two optimisation networks with a neural network-based surrogate solver for diffusion inpainting. This novel concept allows us to perform backpropagation based on inpainting results that approximate the solution of the inpainting equation. Without the need for a single inpainting during test time, our deep optimisation accelerates data selection by more than four orders of magnitude compared to common model-based approaches. This provides real-time performance with high quality results.
Funder
H2020 European Research Council
Universität des Saarlandes
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition
Reference72 articles.
1. Masnou S, Morel J-M (1998) Level lines based disocclusion. In: Proceedings of the 1998 IEEE international conference on image processing. Chicago, IL, vol 3, pp 259–263
2. Efros AA, Leung T (1999) Texture synthesis by non-parametric sampling. In: Proceedings of the seventh international conference on computer vision. Kerkyra, Greece, vol 2, pp 1033–1038
3. Bertalmío M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting. In: Proceedings of the SIGGRAPH 2000, New Orleans, LI, pp 417–424
4. Guillemot C, Le Meur O (2014) Image inpainting: overview and recent advances. IEEE Signal Process Mag 31(1):127–144
5. Carlsson S (1988) Sketch based coding of grey level images. Signal Process 15:57–83
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献