{"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/tensorf-tensorial-radiance-fields","title":"TensoRF: Tensorial Radiance Fields","arxiv_id":"2203.09517","date":"2022-03-17","proceeding":null,"authors":["Anpei Chen","Zexiang Xu","Andreas Geiger","Jingyi Yu","Hao Su"],"abstract":"We present TensoRF, a novel approach to model and reconstruct radiance fields. Unlike NeRF that purely uses MLPs, we model the radiance field of a scene as a 4D tensor, which represents a 3D voxel grid with per-voxel multi-channel features. Our central idea is to factorize the 4D scene tensor into multiple compact low-rank tensor components. We demonstrate that applying traditional CP decomposition -- that factorizes tensors into rank-one components with compact vectors -- in our framework leads to improvements over vanilla NeRF. To further boost performance, we introduce a novel vector-matrix (VM) decomposition that relaxes the low-rank constraints for two modes of a tensor and factorizes tensors into compact vector and matrix factors. Beyond superior rendering quality, our models with CP and VM decompositions lead to a significantly lower memory footprint in comparison to previous and concurrent works that directly optimize per-voxel features. Experimentally, we demonstrate that TensoRF with CP decomposition achieves fast reconstruction (<30 min) with better rendering quality and even a smaller model size (<4 MB) compared to NeRF. Moreover, TensoRF with VM decomposition further boosts rendering quality and outperforms previous state-of-the-art methods, while reducing the reconstruction time (<10 min) and retaining a compact model size (<75 MB).","url_abs":"https://arxiv.org/abs/2203.09517v2","url_pdf":"https://arxiv.org/pdf/2203.09517v2.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":"tensorf-tensorial-radiance-fields","repo_url":"https://github.com/apchenstu/TensoRF","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorf-tensorial-radiance-fields","repo_url":"https://github.com/ashawkey/torch-ngp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"low-dose-x-ray-ct-reconstruction","task_name":"Low-Dose X-Ray Ct Reconstruction"},{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"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":"TensoRF","rank_in_archive_order":3,"of":9,"metrics":{"PSNR":"33.78","SSIM":"0.9387"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-x3d","task":"Novel View Synthesis","dataset":"X3D","model":"TensoRF","rank_in_archive_order":3,"of":6,"metrics":{"PSNR":"37.67","SSIM":"0.9712"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.09517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09517"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ashawkey/torch-ngp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/apchenstu/TensoRF","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"37858228c2f2e7ba","entry":"NeRFNetwork","repo":"ashawkey/torch-ngp","repo_kind":"listed","path":"tensoRF/network.py","file_url":"https://github.com/ashawkey/torch-ngp/blob/HEAD/tensoRF/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37858228c2f2e7ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}