{"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/mair-multi-view-attention-inverse-rendering","title":"MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation","arxiv_id":"2303.12368","date":"2023-03-22","proceeding":"CVPR 2023 1","authors":["Junyong Choi","SeokYeong Lee","Haesol Park","Seung-Won Jung","Ig-Jae Kim","Junghyun Cho"],"abstract":"We propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-view images provide a variety of information about the scene, multi-view images in object-level inverse rendering have been taken for granted. However, owing to the absence of multi-view HDR synthetic dataset, scene-level inverse rendering has mainly been studied using single-view image. We were able to successfully perform scene-level inverse rendering using multi-view images by expanding OpenRooms dataset and designing efficient pipelines to handle multi-view images, and splitting spatially-varying lighting. Our experiments show that the proposed method not only achieves better performance than single-view-based methods, but also achieves robust performance on unseen real-world scene. Also, our sophisticated 3D spatially-varying lighting volume allows for photorealistic object insertion in any 3D location.","url_abs":"https://arxiv.org/abs/2303.12368v2","url_pdf":"https://arxiv.org/pdf/2303.12368v2.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":"mair-multi-view-attention-inverse-rendering","repo_url":"https://github.com/bring728/MAIR_Open","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inverse-rendering","task_name":"Inverse Rendering"},{"task_slug":"lighting-estimation","task_name":"Lighting Estimation"}],"methods":[],"datasets_introduced":[{"slug":"openrooms-ff","name":"OpenRooms FF","full_name":"OpenRooms Forward Facing"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.12368","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}