{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/painting-outside-the-box-image-outpainting","title":"Painting Outside the Box: Image Outpainting with GANs","arxiv_id":"1808.08483","date":"2018-08-25","proceeding":null,"authors":["Mark Sabini","Gili Rusak"],"abstract":"The challenging task of image outpainting (extrapolation) has received\ncomparatively little attention in relation to its cousin, image inpainting\n(completion). Accordingly, we present a deep learning approach based on Iizuka\net al. for adversarially training a network to hallucinate past image\nboundaries. We use a three-phase training schedule to stably train a DCGAN\narchitecture on a subset of the Places365 dataset. In line with Iizuka et al.,\nwe also use local discriminators to enhance the quality of our output. Once\ntrained, our model is able to outpaint $128 \\times 128$ color images relatively\nrealistically, thus allowing for recursive outpainting. Our results show that\ndeep learning approaches to image outpainting are both feasible and promising.","url_abs":"http://arxiv.org/abs/1808.08483v1","url_pdf":"http://arxiv.org/pdf/1808.08483v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"painting-outside-the-box-image-outpainting","repo_url":"https://github.com/ShinyCode/image-outpainting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"painting-outside-the-box-image-outpainting","repo_url":"https://github.com/hytxx/image-outpainting-optional-mask","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-outpainting","task_name":"Image Outpainting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.08483","atlas_url":"https://app.syntology.ai/?focus=1808.08483","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}