{"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/unified-depth-prediction-and-intrinsic-image","title":"Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields","arxiv_id":"1603.06359","date":"2016-03-21","proceeding":null,"authors":["Seungryong Kim","Kihong Park","Kwanghoon Sohn","Stephen Lin"],"abstract":"We present a method for jointly predicting a depth map and intrinsic images\nfrom single-image input. The two tasks are formulated in a synergistic manner\nthrough a joint conditional random field (CRF) that is solved using a novel\nconvolutional neural network (CNN) architecture, called the joint convolutional\nneural field (JCNF) model. Tailored to our joint estimation problem, JCNF\ndiffers from previous CNNs in its sharing of convolutional activations and\nlayers between networks for each task, its inference in the gradient domain\nwhere there exists greater correlation between depth and intrinsic images, and\nthe incorporation of a gradient scale network that learns the confidence of\nestimated gradients in order to effectively balance them in the solution. This\napproach is shown to surpass state-of-the-art methods both on single-image\ndepth estimation and on intrinsic image decomposition.","url_abs":"http://arxiv.org/abs/1603.06359v1","url_pdf":"http://arxiv.org/pdf/1603.06359v1.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":"unified-depth-prediction-and-intrinsic-image","repo_url":"https://github.com/seungryong/JCNF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"intrinsic-image-decomposition","task_name":"Intrinsic Image Decomposition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1603.06359","atlas_url":"https://app.syntology.ai/?focus=1603.06359","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}