{"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/learning-multi-scale-local-conditional","title":"Learning multi-scale local conditional probability models of images","arxiv_id":"2303.02984","date":"2023-03-06","proceeding":null,"authors":["Zahra Kadkhodaie","Florentin Guth","Stéphane Mallat","Eero P Simoncelli"],"abstract":"Deep neural networks can learn powerful prior probability models for images, as evidenced by the high-quality generations obtained with recent score-based diffusion methods. But the means by which these networks capture complex global statistical structure, apparently without suffering from the curse of dimensionality, remain a mystery. To study this, we incorporate diffusion methods into a multi-scale decomposition, reducing dimensionality by assuming a stationary local Markov model for wavelet coefficients conditioned on coarser-scale coefficients. We instantiate this model using convolutional neural networks (CNNs) with local receptive fields, which enforce both the stationarity and Markov properties. Global structures are captured using a CNN with receptive fields covering the entire (but small) low-pass image. We test this model on a dataset of face images, which are highly non-stationary and contain large-scale geometric structures. Remarkably, denoising, super-resolution, and image synthesis results all demonstrate that these structures can be captured with significantly smaller conditioning neighborhoods than required by a Markov model implemented in the pixel domain. Our results show that score estimation for large complex images can be reduced to low-dimensional Markov conditional models across scales, alleviating the curse of dimensionality.","url_abs":"https://arxiv.org/abs/2303.02984v1","url_pdf":"https://arxiv.org/pdf/2303.02984v1.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":"learning-multi-scale-local-conditional","repo_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.02984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02984"}},"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/labforcomputationalvision/local-probability-models-of-images","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":13},"by_repo_kind":{"official":{"samples":16,"ran":3,"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":"eb15c404ffac080f","entry":"MSE","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/quality_metrics_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/quality_metrics_func.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":"eb15c404ffac080f"}},{"code_sha256_prefix":"98dacb3ad56237ba","entry":"calc_jacobian_rows","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/linear_approx.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/linear_approx.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":"98dacb3ad56237ba"}},{"code_sha256_prefix":"31ac25abb6e95520","entry":"load_set14","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/dataloader_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/dataloader_func.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":"31ac25abb6e95520"}},{"code_sha256_prefix":"4b72bc0d1ff5c887","entry":"batch_ave_psnr_torch","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/quality_metrics_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/quality_metrics_func.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":"4b72bc0d1ff5c887"}},{"code_sha256_prefix":"3d963b040f8c9cc8","entry":"batch_psnr_numpy","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/quality_metrics_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/quality_metrics_func.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":"3d963b040f8c9cc8"}},{"code_sha256_prefix":"41d00d5409b3c2fd","entry":"calc_jacobian","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/linear_approx.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/linear_approx.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":"41d00d5409b3c2fd"}},{"code_sha256_prefix":"53ef977c62a678b6","entry":"calc_jacobian_row_MS","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/linear_approx.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/linear_approx.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":"53ef977c62a678b6"}},{"code_sha256_prefix":"ed636e6ae81c20f6","entry":"decompose","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/wavelet_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/wavelet_func.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":"ed636e6ae81c20f6"}},{"code_sha256_prefix":"097ed9b3a930e7e9","entry":"init_BF_CNN","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/model_loader_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/model_loader_func.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":"097ed9b3a930e7e9"}},{"code_sha256_prefix":"d8c46e305d61032b","entry":"init_BF_CNN_RF","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/model_loader_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/model_loader_func.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":"d8c46e305d61032b"}},{"code_sha256_prefix":"7debb2bf8982b29f","entry":"load_CelebA_HQ_dataset","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/dataloader_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/dataloader_func.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":"7debb2bf8982b29f"}},{"code_sha256_prefix":"07c6a66c70cb9fd7","entry":"load_CelebA_dataset","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/dataloader_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/dataloader_func.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":"07c6a66c70cb9fd7"}},{"code_sha256_prefix":"cfa3a920c42c6c1c","entry":"multi_scale_decompose","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/wavelet_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/wavelet_func.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":"cfa3a920c42c6c1c"}},{"code_sha256_prefix":"1da008584ab89491","entry":"one_scale_synthesis","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/algorithm_inv_prob.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/algorithm_inv_prob.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":"1da008584ab89491"}},{"code_sha256_prefix":"8a23b3b8f3102d5d","entry":"read_trained_params","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/model_loader_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/model_loader_func.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":"8a23b3b8f3102d5d"}},{"code_sha256_prefix":"24f5f171a4fc9e72","entry":"reconstruct","repo":"labforcomputationalvision/local-probability-models-of-images","repo_kind":"official","path":"code/wavelet_func.py","file_url":"https://github.com/labforcomputationalvision/local-probability-models-of-images/blob/HEAD/code/wavelet_func.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":"24f5f171a4fc9e72"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}