Wide-Context Semantic Image Extrapolation
By Yi Wang, Xin Tao, Xiaoyong Shen, Jiaya Jia. 2019
115 citations recorded by the source corpus.
This paper studies the fundamental problem of extrapolating visual context using deep generative models, i.e., extending image borders with plausible structure and details. This seemingly easy task actually faces many crucial technical challenges and has its unique properties. The two major issues are size expansion and one-side constraints. We propose a semantic regeneration network with several special contributions and use multiple spatial related losses to address these issues. Our results contain consistent structures and high-quality textures. Extensive experiments are conducted on various possible alternatives and related methods. We also explore the potential of our method for various interesting applications that can benefit research in a variety of fields.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Andrea Vedaldi
- Jitendra Malik
- Andrew Zisserman
- Trevor Darrell
- Xiaogang Wang
Citations in the corpus
- Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (2021, methodology): “We follow the common setting (DeVries et al., 2019; Wang et al., 2019b) on the edges to photos datasets (Isola et al., 2017) at 256×256 resolution, where FID samples once per validation image (200 in total) and the training set is used as the reference distribution; LPIPS measures the…”
- Palette: Image-to-Image Diffusion Models (2021, methodology): “While other uncropping methods exist (e.g., [Guo et al. 2020; Wang et al. 2019b]), we only compare with two representative methods.”
- Boundless: Generative Adversarial Networks for Image Extension (2019, result): “Concurrent to our work is [44], which is similar to ours but does not condition the discriminator with pre-trained features.”
- InOut: Diverse Image Outpainting via GAN Inversion (2021, unknown): “Recently, several approaches [27, 29, 31] apply GAN models and formulate the problem as an image-to-image translation task.”
- SynSin: End-to-End View Synthesis From a Single Image (2019, methodology): “Deep networks have been previously applied to inpainting [46, 61, 66].”