{"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/parallel-inversion-of-neural-radiance-fields","title":"Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation","arxiv_id":"2210.10108","date":"2022-10-18","proceeding":null,"authors":["Yunzhi Lin","Thomas Müller","Jonathan Tremblay","Bowen Wen","Stephen Tyree","Alex Evans","Patricio A. Vela","Stan Birchfield"],"abstract":"We present a parallelized optimization method based on fast Neural Radiance Fields (NeRF) for estimating 6-DoF pose of a camera with respect to an object or scene. Given a single observed RGB image of the target, we can predict the translation and rotation of the camera by minimizing the residual between pixels rendered from a fast NeRF model and pixels in the observed image. We integrate a momentum-based camera extrinsic optimization procedure into Instant Neural Graphics Primitives, a recent exceptionally fast NeRF implementation. By introducing parallel Monte Carlo sampling into the pose estimation task, our method overcomes local minima and improves efficiency in a more extensive search space. We also show the importance of adopting a more robust pixel-based loss function to reduce error. Experiments demonstrate that our method can achieve improved generalization and robustness on both synthetic and real-world benchmarks.","url_abs":"https://arxiv.org/abs/2210.10108v2","url_pdf":"https://arxiv.org/pdf/2210.10108v2.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":"parallel-inversion-of-neural-radiance-fields","repo_url":"https://github.com/NVlabs/ParallelInversion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.10108","atlas_url":"https://app.syntology.ai/?focus=2210.10108","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}