pith. sign in

arxiv: 1711.09345 · v1 · pith:JCQDTUQTnew · submitted 2017-11-26 · 💻 cs.CV

Semantically Consistent Image Completion with Fine-grained Details

classification 💻 cs.CV
keywords imageadversarialcompletionperceptualachievecontentsdetailsdifferent
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Perceptually Motivated Method for Image Inpainting Comparison

    cs.CV 2019-07 unverdicted novelty 6.0

    Subjective comparison of nine inpainting algorithms produces proposed objective metrics with high correlation to human perception of realism.