{"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/neat-neural-adaptive-tomography","title":"NeAT: Neural Adaptive Tomography","arxiv_id":"2202.02171","date":"2022-02-04","proceeding":null,"authors":["Darius Rückert","Yuanhao Wang","Rui Li","Ramzi Idoughi","Wolfgang Heidrich"],"abstract":"In this paper, we present Neural Adaptive Tomography (NeAT), the first adaptive, hierarchical neural rendering pipeline for multi-view inverse rendering. Through a combination of neural features with an adaptive explicit representation, we achieve reconstruction times far superior to existing neural inverse rendering methods. The adaptive explicit representation improves efficiency by facilitating empty space culling and concentrating samples in complex regions, while the neural features act as a neural regularizer for the 3D reconstruction. The NeAT framework is designed specifically for the tomographic setting, which consists only of semi-transparent volumetric scenes instead of opaque objects. In this setting, NeAT outperforms the quality of existing optimization-based tomography solvers while being substantially faster.","url_abs":"https://arxiv.org/abs/2202.02171v1","url_pdf":"https://arxiv.org/pdf/2202.02171v1.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":"neat-neural-adaptive-tomography","repo_url":"https://github.com/darglein/NeAT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"inverse-rendering","task_name":"Inverse Rendering"},{"task_slug":"low-dose-x-ray-ct-reconstruction","task_name":"Low-Dose X-Ray Ct Reconstruction"},{"task_slug":"neural-rendering","task_name":"Neural Rendering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/low-dose-x-ray-ct-reconstruction-on-x3d","task":"Low-Dose X-Ray Ct Reconstruction","dataset":"X3D","model":"NeAT","rank_in_archive_order":4,"of":9,"metrics":{"PSNR":"33.41","SSIM":"0.9447"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.02171","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}