Papers › Unsupervised Semantic Correspondence Using Stable Diffusion

Unsupervised Semantic Correspondence Using Stable Diffusion

24 May 2023NeurIPS 2023 11arXiv:2305.15581archive 2025-07-28

Eric Hedlin, Gopal Sharma, Shweta Mahajan, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi

Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the semantics of the objects they are asked to generate. In this work we show that, without any training, one can leverage this semantic knowledge within diffusion models to find semantic correspondences - locations in multiple images that have the same semantic meaning. Specifically, given an image, we optimize the prompt embeddings of these models for maximum attention on the regions of interest. These optimized embeddings capture semantic information about the location, which can then be transferred to another image. By doing so we obtain results on par with the strongly supervised state of the art on the PF-Willow dataset and significantly outperform (20.9% relative for the SPair-71k dataset) any existing weakly or unsupervised method on PF-Willow, CUB-200 and SPair-71k datasets.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.15581")

Code

Syntology Ran 4 of 12 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong.

By repository: official repository: 12 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ubc-vision/LDM_correspondences officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 4 ran; 1 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
8unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ubc-vision/LDM_correspondences. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

boolean_string ubc-vision/LDM_correspondences/utils/utils.py official repository ran · violated contract Apache-2.0 (permissive) · b1f9cebf0d177140 · report
init_latent ubc-vision/LDM_correspondences/utils/ptp_utils.py official repository ran · our draft was wrong Apache-2.0 (permissive) · caadc5c4b7627e0c · report
latent2image ubc-vision/LDM_correspondences/utils/ptp_utils.py official repository ran · our draft was wrong Apache-2.0 (permissive) · e3c3bb87bbe9b4a7 · report
load_512 ubc-vision/LDM_correspondences/utils/optimize_token.py official repository ran · honoured contract Apache-2.0 (permissive) · 0230471a58926463 · report
diffusion_step ubc-vision/LDM_correspondences/utils/ptp_utils.py official repository unverified Apache-2.0 (permissive) · a9127186bb55b3f4 · report
find_knn ubc-vision/LDM_correspondences/eval/dataset.py official repository unverified Apache-2.0 (permissive) · d743428e092c7a2d · report
get_confirm_token ubc-vision/LDM_correspondences/eval/download.py official repository unverified Apache-2.0 (permissive) · 988fd31ae49fff76 · report
load_checkpoint ubc-vision/LDM_correspondences/utils/utils.py official repository unverified Apache-2.0 (permissive) · 0e293426913c9cf4 · report
load_dataset ubc-vision/LDM_correspondences/eval/download.py official repository unverified Apache-2.0 (permissive) · d2ba3f4063f64a9f · report
parse_list ubc-vision/LDM_correspondences/utils/utils.py official repository unverified Apache-2.0 (permissive) · 7e8f8e2a3ea7f64e · report
random_crop ubc-vision/LDM_correspondences/eval/dataset.py official repository unverified Apache-2.0 (permissive) · d7fccb2844458579 · report
resize ubc-vision/LDM_correspondences/eval/dataset.py official repository unverified Apache-2.0 (permissive) · 3c8be19016fde613 · report

Tasks

Semantic correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic correspondence CUB-200-2011 LDM Correspondences Mean PCK@0.05 61.6 #1 of 1 Archive leaderboard report
Semantic correspondence CUB-200-2011 LDM Correspondences Mean PCK@0.1 77.5 #1 of 1 Archive leaderboard report
Semantic correspondence PF-WILLOW LDMCorrespondences PCK 84.3 #1 of 8 Archive leaderboard report
Semantic correspondence SPair-71k LDMCorrespondences PCK 45.4 #18 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections