{"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/scribbler-controlling-deep-image-synthesis","title":"Scribbler: Controlling Deep Image Synthesis with Sketch and Color","arxiv_id":"1612.00835","date":"2016-12-02","proceeding":"CVPR 2017 7","authors":["Patsorn Sangkloy","Jingwan Lu","Chen Fang","Fisher Yu","James Hays"],"abstract":"Recently, there have been several promising methods to generate realistic\nimagery from deep convolutional networks. These methods sidestep the\ntraditional computer graphics rendering pipeline and instead generate imagery\nat the pixel level by learning from large collections of photos (e.g. faces or\nbedrooms). However, these methods are of limited utility because it is\ndifficult for a user to control what the network produces. In this paper, we\npropose a deep adversarial image synthesis architecture that is conditioned on\nsketched boundaries and sparse color strokes to generate realistic cars,\nbedrooms, or faces. We demonstrate a sketch based image synthesis system which\nallows users to 'scribble' over the sketch to indicate preferred color for\nobjects. Our network can then generate convincing images that satisfy both the\ncolor and the sketch constraints of user. The network is feed-forward which\nallows users to see the effect of their edits in real time. We compare to\nrecent work on sketch to image synthesis and show that our approach can\ngenerate more realistic, more diverse, and more controllable outputs. The\narchitecture is also effective at user-guided colorization of grayscale images.","url_abs":"http://arxiv.org/abs/1612.00835v2","url_pdf":"http://arxiv.org/pdf/1612.00835v2.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":"scribbler-controlling-deep-image-synthesis","repo_url":"https://github.com/Pingxia/ConvolutionalSketchInversion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"colorization","method_name":"Colorization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.00835","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}