Image inpainting is the task to reconstruct the missing region in an image with plausible contents based on its surrounding context, which is a common topic of low-level computer vision. Making use of this technique, people could restore damaged images or remove unwanted objects from images or videos. In this task, our goal is to not only fill in the plausible contexts with realistic details but also make the inpainted area coherent with the contexts as well as the boundaries.

In spite of recent progress of deep generative models, generating high-resolution images remains a difficult task. This is mainly because modeling the distribution of pixels is difficult and the trained models easily introduce blurry components and artifacts when the dimensionality becomes high. Following [1] which proposes to synthesize an image based on joint optimization of image context and texture constraints, we divide the task into inference and translation as two separate steps and model each step with a deep neural network [2]. We also use simple heuristics to guide the propagation of local textures from the boundary to the hole. Meanwhile, we introduce a novel block-wise procedural training scheme to stabilize the training and propose a new strategy called adversarial annealing to reduce the artifacts [3].

On the other hand, we observe that existing methods based on generative models don’t exploit the segmentation information to constrain the object shapes, which usually lead to blurry results on the boundary. To tackle this problem, we propose to introduce the semantic segmentation information, which disentangles the inter-class difference and intra-class variation for image inpainting [4]. This leads to much clearer recovered boundary between semantically different regions and better texture within semantically consistent segments. Experiments on multiple public datasets show that our approach outperforms existing methods in optimizing the image inpainting quality.

–By Yuhang Song

Reference
[1] Yang, Chao, et al. “High-resolution image inpainting using multi-scale neural patch synthesis.” The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Vol. 1. No. 2. 2017.
[2] Song, Yuhang, et al. “Contextual-based Image Inpainting: Infer, Match, and Translate.” Proceedings of the European Conference on Computer Vision (ECCV). 2018.
[3] Yang, Chao, et al. “Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart.” arXiv preprint arXiv:1803.08943 (2018).
[4] Song, Yuhang, et al. “SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting.” British Machine Vision Conference (BMVC). 2018.