{"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/surfacenet-an-end-to-end-3d-neural-network","title":"SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis","arxiv_id":"1708.01749","date":"2017-08-05","proceeding":"ICCV 2017 10","authors":["Mengqi Ji","Juergen Gall","Haitian Zheng","Yebin Liu","Lu Fang"],"abstract":"This paper proposes an end-to-end learning framework for multiview\nstereopsis. We term the network SurfaceNet. It takes a set of images and their\ncorresponding camera parameters as input and directly infers the 3D model. The\nkey advantage of the framework is that both photo-consistency as well geometric\nrelations of the surface structure can be directly learned for the purpose of\nmultiview stereopsis in an end-to-end fashion. SurfaceNet is a fully 3D\nconvolutional network which is achieved by encoding the camera parameters\ntogether with the images in a 3D voxel representation. We evaluate SurfaceNet\non the large-scale DTU benchmark.","url_abs":"http://arxiv.org/abs/1708.01749v1","url_pdf":"http://arxiv.org/pdf/1708.01749v1.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":"surfacenet-an-end-to-end-3d-neural-network","repo_url":"https://github.com/mjiUST/SurfaceNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"surfacenet-an-end-to-end-3d-neural-network","repo_url":"https://github.com/Mi-Dora/SurfaceNet2D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"surfacenet-an-end-to-end-3d-neural-network","repo_url":"https://github.com/paschalidoud/raynet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.01749","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}