Semantically Consistent Image Completion with Fine-grained Details
This work addresses the challenge of generating detailed and semantically consistent image completions for computer vision applications, representing an incremental improvement over existing GAN-based methods.
The paper tackles the problem of image completion lacking fine-grained details in complex scenes or large holes by introducing a perceptual network for mid-level semantic guidance, achieving nearly seamless fusion results and outperforming existing methods on CelebA Face and Paris StreetView datasets.
Image completion has achieved significant progress due to advances in generative adversarial networks (GANs). Albeit natural-looking, the synthesized contents still lack details, especially for scenes with complex structures or images with large holes. This is because there exists a gap between low-level reconstruction loss and high-level adversarial loss. To address this issue, we introduce a perceptual network to provide mid-level guidance, which measures the semantical similarity between the synthesized and original contents in a similarity-enhanced space. We conduct a detailed analysis on the effects of different losses and different levels of perceptual features in image completion, showing that there exist complementarity between adversarial training and perceptual features. By combining them together, our model can achieve nearly seamless fusion results in an end-to-end manner. Moreover, we design an effective lightweight generator architecture, which can achieve effective image inpainting with far less parameters. Evaluated on CelebA Face and Paris StreetView dataset, our proposed method significantly outperforms existing methods.