101. PEPSI : Fast Image Inpainting With Parallel Decoding Network
- Author
-
Yong-Goo Shin, Sung-Jea Ko, Seung Wook Kim, Seung Hwan Park, and Min-Cheol Sagong
- Subjects
Computer science ,business.industry ,Deep learning ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Inpainting ,02 engineering and technology ,010501 environmental sciences ,01 natural sciences ,Image (mathematics) ,Convolution ,Feature (computer vision) ,Path (graph theory) ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,Algorithm ,Decoding methods ,0105 earth and related environmental sciences - Abstract
Recently, a generative adversarial network (GAN)-based method employing the coarse-to-fine network with the contextual attention module (CAM) has shown outstanding results in image inpainting. However, this method requires numerous computational resources due to its two-stage process for feature encoding. To solve this problem, in this paper, we present a novel network structure, called PEPSI: parallel extended-decoder path for semantic inpainting. PEPSI can reduce the number of convolution operations by adopting a structure consisting of a single shared encoding network and a parallel decoding network with coarse and inpainting paths. The coarse path produces a preliminary inpainting result with which the encoding network is trained to predict features for the CAM. At the same time, the inpainting path creates a higher-quality inpainting result using refined features reconstructed by the CAM. PEPSI not only reduces the number of convolution operation almost by half as compared to the conventional coarse-to-fine networks but also exhibits superior performance to other models in terms of testing time and qualitative scores.
- Published
- 2019