{"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/diffusion-counterfactual-generation-with","title":"Diffusion Counterfactual Generation with Semantic Abduction","arxiv_id":"2506.07883","date":"2025-06-09","proceeding":null,"authors":["Rajat Rasal","Avinash Kori","Fabio De Sousa Ribeiro","Tian Xia","Ben Glocker"],"abstract":"Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal model. While existing auto-encoding frameworks admit semantic latent spaces which can be manipulated for causal control, they struggle with scalability and fidelity. Advancements in diffusion models present opportunities for improving counterfactual image editing, having demonstrated state-of-the-art visual quality, human-aligned perception and representation learning capabilities. Here, we present a suite of diffusion-based causal mechanisms, introducing the notions of spatial, semantic and dynamic abduction. We propose a general framework that integrates semantic representations into diffusion models through the lens of Pearlian causality to edit images via a counterfactual reasoning process. To our knowledge, this is the first work to consider high-level semantic identity preservation for diffusion counterfactuals and to demonstrate how semantic control enables principled trade-offs between faithful causal control and identity preservation.","url_abs":"https://arxiv.org/abs/2506.07883v1","url_pdf":"https://arxiv.org/pdf/2506.07883v1.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":"diffusion-counterfactual-generation-with","repo_url":"https://github.com/rajatrasal/diffusion-counterfactuals","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"counterfactual-reasoning","task_name":"Counterfactual Reasoning"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"counterfactuals","method_name":"Counterfactuals"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.07883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07883"}},"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/rajatrasal/diffusion-counterfactuals","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"8afb07a694e85597","entry":"evaluate_classifier","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"model/classifier.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/classifier.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":"8afb07a694e85597"}},{"code_sha256_prefix":"cb62c7e81fb0b39f","entry":"get_betas","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"model/utils/diffusion.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/utils/diffusion.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":"cb62c7e81fb0b39f"}},{"code_sha256_prefix":"59fde1116ac21980","entry":"get_torchvision_transforms","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"model/dataset.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/dataset.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":"59fde1116ac21980"}},{"code_sha256_prefix":"5d47dd69d34460d0","entry":"load_idx","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"model/mnist.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/mnist.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":"5d47dd69d34460d0"}},{"code_sha256_prefix":"d7b2b0a5c2a807f7","entry":"load_image_pillow","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"model/dataset.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/dataset.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":"d7b2b0a5c2a807f7"}},{"code_sha256_prefix":"0e3efa6fd931c56f","entry":"load_morphomnist_like","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"model/mnist.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/mnist.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":"0e3efa6fd931c56f"}},{"code_sha256_prefix":"42a6db49eebe4a0a","entry":"metrics","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"benchmarking/celeba_f1.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/benchmarking/celeba_f1.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":"42a6db49eebe4a0a"}},{"code_sha256_prefix":"f1703a9e979afe6b","entry":"metrics","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"benchmarking/celeba_nto.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/benchmarking/celeba_nto.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":"f1703a9e979afe6b"}},{"code_sha256_prefix":"e8a4d61a5fec68dd","entry":"normalise","repo":"rajatrasal/diffusion-counterfactuals","repo_kind":"official","path":"model/mnist.py","file_url":"https://github.com/rajatrasal/diffusion-counterfactuals/blob/HEAD/model/mnist.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":"e8a4d61a5fec68dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}