{"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-a-multi-view-stereo-machine","title":"Learning a Multi-View Stereo Machine","arxiv_id":"1708.05375","date":"2017-08-17","proceeding":"NeurIPS 2017 12","authors":["Abhishek Kar","Christian Häne","Jitendra Malik"],"abstract":"We present a learnt system for multi-view stereopsis. In contrast to recent\nlearning based methods for 3D reconstruction, we leverage the underlying 3D\ngeometry of the problem through feature projection and unprojection along\nviewing rays. By formulating these operations in a differentiable manner, we\nare able to learn the system end-to-end for the task of metric 3D\nreconstruction. End-to-end learning allows us to jointly reason about shape\npriors while conforming geometric constraints, enabling reconstruction from\nmuch fewer images (even a single image) than required by classical approaches\nas well as completion of unseen surfaces. We thoroughly evaluate our approach\non the ShapeNet dataset and demonstrate the benefits over classical approaches\nas well as recent learning based methods.","url_abs":"http://arxiv.org/abs/1708.05375v1","url_pdf":"http://arxiv.org/pdf/1708.05375v1.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-a-multi-view-stereo-machine","repo_url":"https://github.com/akar43/lsm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-geometry","task_name":"3D geometry"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.05375","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}