{"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/emergent-correspondence-from-image-diffusion","title":"Emergent Correspondence from Image Diffusion","arxiv_id":"2306.03881","date":"2023-06-06","proceeding":"NeurIPS 2023 11","authors":["Luming Tang","Menglin Jia","Qianqian Wang","Cheng Perng Phoo","Bharath Hariharan"],"abstract":"Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images. Without any additional fine-tuning or supervision on the task-specific data or annotations, DIFT is able to outperform both weakly-supervised methods and competitive off-the-shelf features in identifying semantic, geometric, and temporal correspondences. Particularly for semantic correspondence, DIFT from Stable Diffusion is able to outperform DINO and OpenCLIP by 19 and 14 accuracy points respectively on the challenging SPair-71k benchmark. It even outperforms the state-of-the-art supervised methods on 9 out of 18 categories while remaining on par for the overall performance. Project page: https://diffusionfeatures.github.io","url_abs":"https://arxiv.org/abs/2306.03881v2","url_pdf":"https://arxiv.org/pdf/2306.03881v2.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":"emergent-correspondence-from-image-diffusion","repo_url":"https://github.com/Tsingularity/dift","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"emergent-correspondence-from-image-diffusion","repo_url":"https://github.com/mirthAI/RetinaRegNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dino","method_name":"DINO"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.03881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03881"}},"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/Tsingularity/dift","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mirthAI/RetinaRegNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"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":"d4504f24084fa259","entry":"generate_read_function","repo":"Tsingularity/dift","repo_kind":"listed","path":"eval_homography.py","file_url":"https://github.com/Tsingularity/dift/blob/HEAD/eval_homography.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":"d4504f24084fa259"}},{"code_sha256_prefix":"fb8cfa5fec0b7558","entry":"interpolate_pos_encoding","repo":"Tsingularity/dift","repo_kind":"listed","path":"src/models/clip.py","file_url":"https://github.com/Tsingularity/dift/blob/HEAD/src/models/clip.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":"fb8cfa5fec0b7558"}},{"code_sha256_prefix":"c204ffb4194a785f","entry":"label_propagation","repo":"Tsingularity/dift","repo_kind":"listed","path":"eval_davis.py","file_url":"https://github.com/Tsingularity/dift/blob/HEAD/eval_davis.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":"c204ffb4194a785f"}},{"code_sha256_prefix":"7ae0014e69c4f92c","entry":"mnn_matcher","repo":"Tsingularity/dift","repo_kind":"listed","path":"eval_homography.py","file_url":"https://github.com/Tsingularity/dift/blob/HEAD/eval_homography.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":"7ae0014e69c4f92c"}},{"code_sha256_prefix":"e015f2c93c762aff","entry":"norm_mask","repo":"Tsingularity/dift","repo_kind":"listed","path":"eval_davis.py","file_url":"https://github.com/Tsingularity/dift/blob/HEAD/eval_davis.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":"e015f2c93c762aff"}},{"code_sha256_prefix":"efc78e753491eeab","entry":"restrict_neighborhood","repo":"Tsingularity/dift","repo_kind":"listed","path":"eval_davis.py","file_url":"https://github.com/Tsingularity/dift/blob/HEAD/eval_davis.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":"efc78e753491eeab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}