{"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/learning-to-synthesize-a-4d-rgbd-light-field","title":"Learning to Synthesize a 4D RGBD Light Field from a Single Image","arxiv_id":"1708.03292","date":"2017-08-10","proceeding":"ICCV 2017 10","authors":["Pratul P. Srinivasan","Tongzhou Wang","Ashwin Sreelal","Ravi Ramamoorthi","Ren Ng"],"abstract":"We present a machine learning algorithm that takes as input a 2D RGB image\nand synthesizes a 4D RGBD light field (color and depth of the scene in each ray\ndirection). For training, we introduce the largest public light field dataset,\nconsisting of over 3300 plenoptic camera light fields of scenes containing\nflowers and plants. Our synthesis pipeline consists of a convolutional neural\nnetwork (CNN) that estimates scene geometry, a stage that renders a Lambertian\nlight field using that geometry, and a second CNN that predicts occluded rays\nand non-Lambertian effects. Our algorithm builds on recent view synthesis\nmethods, but is unique in predicting RGBD for each light field ray and\nimproving unsupervised single image depth estimation by enforcing consistency\nof ray depths that should intersect the same scene point. Please see our\nsupplementary video at https://youtu.be/yLCvWoQLnms","url_abs":"http://arxiv.org/abs/1708.03292v1","url_pdf":"http://arxiv.org/pdf/1708.03292v1.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":"learning-to-synthesize-a-4d-rgbd-light-field","repo_url":"https://github.com/pratulsrinivasan/Local_Light_Field_Synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.03292","atlas_url":"https://app.syntology.ai/?focus=1708.03292","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}