{"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/continuous-time-functional-diffusion","title":"Continuous-Time Functional Diffusion Processes","arxiv_id":"2303.00800","date":"2023-03-01","proceeding":"NeurIPS 2023 11","authors":["Giulio Franzese","Giulio Corallo","Simone Rossi","Markus Heinonen","Maurizio Filippone","Pietro Michiardi"],"abstract":"We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework to describe the forward and backward dynamics, and several extensions to derive practical training objectives. These include infinite-dimensional versions of Girsanov theorem, in order to be able to compute an ELBO, and of the sampling theorem, in order to guarantee that functional evaluations in a countable set of points are equivalent to infinite-dimensional functions. We use FDPs to build a new breed of generative models in function spaces, which do not require specialized network architectures, and that can work with any kind of continuous data. Our results on real data show that FDPs achieve high-quality image generation, using a simple MLP architecture with orders of magnitude fewer parameters than existing diffusion models.","url_abs":"https://arxiv.org/abs/2303.00800v3","url_pdf":"https://arxiv.org/pdf/2303.00800v3.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":"continuous-time-functional-diffusion","repo_url":"https://github.com/giulio98/functional-diffusion-processes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-celeba-64x64","task":"Image Generation","dataset":"CelebA 64x64","model":"FDP(UViT)","rank_in_archive_order":26,"of":39,"metrics":{"FID":"11","FID_CLIP":"6.55"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-64x64","task":"Image Generation","dataset":"CelebA 64x64","model":"FDP(MLP)","rank_in_archive_order":33,"of":39,"metrics":{"FID":"35","FID_CLIP":"12.44"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.00800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.00800"}},"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/giulio98/functional-diffusion-processes","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"0c65d4efd8f0a6a0","entry":"central_crop","repo":"giulio98/functional-diffusion-processes","repo_kind":"official","path":"src/functional_diffusion_processes/datasets/dataset_utils.py","file_url":"https://github.com/giulio98/functional-diffusion-processes/blob/HEAD/src/functional_diffusion_processes/datasets/dataset_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0c65d4efd8f0a6a0"}},{"code_sha256_prefix":"355ae31ad66b7e7c","entry":"load_dataset_stats","repo":"giulio98/functional-diffusion-processes","repo_kind":"official","path":"src/functional_diffusion_processes/metrics/metrics_utils.py","file_url":"https://github.com/giulio98/functional-diffusion-processes/blob/HEAD/src/functional_diffusion_processes/metrics/metrics_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"355ae31ad66b7e7c"}},{"code_sha256_prefix":"938d1651628085f0","entry":"resize_small","repo":"giulio98/functional-diffusion-processes","repo_kind":"official","path":"src/functional_diffusion_processes/datasets/dataset_utils.py","file_url":"https://github.com/giulio98/functional-diffusion-processes/blob/HEAD/src/functional_diffusion_processes/datasets/dataset_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"938d1651628085f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}