{"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/dense-3d-point-cloud-reconstruction-using-a","title":"Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network","arxiv_id":"1901.08906","date":"2019-01-25","proceeding":null,"authors":["Priyanka Mandikal","R. Venkatesh Babu"],"abstract":"Reconstructing a high-resolution 3D model of an object is a challenging task\nin computer vision. Designing scalable and light-weight architectures is\ncrucial while addressing this problem. Existing point-cloud based\nreconstruction approaches directly predict the entire point cloud in a single\nstage. Although this technique can handle low-resolution point clouds, it is\nnot a viable solution for generating dense, high-resolution outputs. In this\nwork, we introduce DensePCR, a deep pyramidal network for point cloud\nreconstruction that hierarchically predicts point clouds of increasing\nresolution. Towards this end, we propose an architecture that first predicts a\nlow-resolution point cloud, and then hierarchically increases the resolution by\naggregating local and global point features to deform a grid. Our method\ngenerates point clouds that are accurate, uniform and dense. Through extensive\nquantitative and qualitative evaluation on synthetic and real datasets, we\ndemonstrate that DensePCR outperforms the existing state-of-the-art point cloud\nreconstruction works, while also providing a light-weight and scalable\narchitecture for predicting high-resolution outputs.","url_abs":"http://arxiv.org/abs/1901.08906v1","url_pdf":"http://arxiv.org/pdf/1901.08906v1.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":"dense-3d-point-cloud-reconstruction-using-a","repo_url":"https://github.com/val-iisc/densepcr","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-point-cloud-reconstruction","task_name":"3D Point Cloud Reconstruction"},{"task_slug":"point-cloud-reconstruction","task_name":"Point cloud reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1901.08906","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}