{"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/diffusionerf-regularizing-neural-radiance","title":"DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models","arxiv_id":"2302.12231","date":"2023-02-23","proceeding":"CVPR 2023 1","authors":["Jamie Wynn","Daniyar Turmukhambetov"],"abstract":"Under good conditions, Neural Radiance Fields (NeRFs) have shown impressive results on novel view synthesis tasks. NeRFs learn a scene's color and density fields by minimizing the photometric discrepancy between training views and differentiable renderings of the scene. Once trained from a sufficient set of views, NeRFs can generate novel views from arbitrary camera positions. However, the scene geometry and color fields are severely under-constrained, which can lead to artifacts, especially when trained with few input views. To alleviate this problem we learn a prior over scene geometry and color, using a denoising diffusion model (DDM). Our DDM is trained on RGBD patches of the synthetic Hypersim dataset and can be used to predict the gradient of the logarithm of a joint probability distribution of color and depth patches. We show that, these gradients of logarithms of RGBD patch priors serve to regularize geometry and color of a scene. During NeRF training, random RGBD patches are rendered and the estimated gradient of the log-likelihood is backpropagated to the color and density fields. Evaluations on LLFF, the most relevant dataset, show that our learned prior achieves improved quality in the reconstructed geometry and improved generalization to novel views. Evaluations on DTU show improved reconstruction quality among NeRF methods.","url_abs":"https://arxiv.org/abs/2302.12231v3","url_pdf":"https://arxiv.org/pdf/2302.12231v3.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":"diffusionerf-regularizing-neural-radiance","repo_url":"https://github.com/nianticlabs/diffusionerf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.12231","atlas_url":"https://app.syntology.ai/?focus=2302.12231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12231"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/nianticlabs/diffusionerf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"b2afea570d511657","entry":"convert_activation","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"ffmlp/ffmlp.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/ffmlp/ffmlp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2afea570d511657"}},{"code_sha256_prefix":"5ca70dba4b451eee","entry":"get_encoder","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"encoding.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/encoding.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ca70dba4b451eee"}},{"code_sha256_prefix":"00979fadb02bf8df","entry":"huber_loss","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"loss.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00979fadb02bf8df"}},{"code_sha256_prefix":"b005da476fb7a4d2","entry":"make_4x4_transform","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"nerf/circle_path.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/nerf/circle_path.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b005da476fb7a4d2"}},{"code_sha256_prefix":"882a796b52a505e5","entry":"make_circle_path","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"nerf/circle_path.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/nerf/circle_path.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"882a796b52a505e5"}},{"code_sha256_prefix":"f393a4c3336141fb","entry":"make_opt_for_scene","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"nerf/evaluate.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/nerf/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f393a4c3336141fb"}},{"code_sha256_prefix":"ddcd1a350d11a260","entry":"mape_loss","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"loss.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddcd1a350d11a260"}},{"code_sha256_prefix":"c700c0222e7b80ba","entry":"apply_4x4_transform_to_3d_vec","repo":"nianticlabs/diffusionerf","repo_kind":"official","path":"nerf/circle_path.py","file_url":"https://github.com/nianticlabs/diffusionerf/blob/HEAD/nerf/circle_path.py","link_basis":"harvester_set","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":"c700c0222e7b80ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}