{"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-estimate-indoor-lighting-from-3d","title":"Learning to Estimate Indoor Lighting from 3D Objects","arxiv_id":"1806.03994","date":"2018-06-11","proceeding":"3DV 2018 - International Conference on 3D Vision 2018 9","authors":["Henrique Weber","Donald Prévost","Jean-François Lalonde"],"abstract":"In this work, we propose a step towards a more accurate prediction of the\nenvironment light given a single picture of a known object. To achieve this, we\ndeveloped a deep learning method that is able to encode the latent space of\nindoor lighting using few parameters and that is trained on a database of\nenvironment maps. This latent space is then used to generate predictions of the\nlight that are both more realistic and accurate than previous methods. To\nachieve this, our first contribution is a deep autoencoder which is capable of\nlearning the feature space that compactly models lighting. Our second\ncontribution is a convolutional neural network that predicts the light from a\nsingle image of a known object. To train these networks, our third contribution\nis a novel dataset that contains 21,000 HDR indoor environment maps. The\nresults indicate that the predictor can generate plausible lighting estimations\neven from diffuse objects.","url_abs":"http://arxiv.org/abs/1806.03994v3","url_pdf":"http://arxiv.org/pdf/1806.03994v3.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-estimate-indoor-lighting-from-3d","repo_url":"https://github.com/weberhen/learning_indoor_lighting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03994","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}