Papers › Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

28 Nov 2023CVPR 2024 1arXiv:2311.17034archive 2025-07-28

Junyi Zhang, Charles Herrmann, Junhwa Hur, Eric Chen, Varun Jampani, Deqing Sun, Ming-Hsuan Yang

While pre-trained large-scale vision models have shown significant promise for semantic correspondence, their features often struggle to grasp the geometry and orientation of instances. This paper identifies the importance of being geometry-aware for semantic correspondence and reveals a limitation of the features of current foundation models under simple post-processing. We show that incorporating this information can markedly enhance semantic correspondence performance with simple but effective solutions in both zero-shot and supervised settings. We also construct a new challenging benchmark for semantic correspondence built from an existing animal pose estimation dataset, for both pre-training validating models. Our method achieves a PCK@0.10 score of 65.4 (zero-shot) and 85.6 (supervised) on the challenging SPair-71k dataset, outperforming the state of the art by 5.5p and 11.0p absolute gains, respectively. Our code and datasets are publicly available at: https://telling-left-from-right.github.io/.

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="2311.17034")

Code

Syntology Ran 11 of 15 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Junyi42/geoaware-sc officialmentioned on GitHubpytorch 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

15 samples harvested; 11 ran; 0 honoured the contract we drafted; 4 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.

2ran · our draft was wrong
9ran
4unverified

Licence: 15 of the 15 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 Junyi42/geoaware-sc. “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.

conv1x1 Junyi42/geoaware-sc/model_utils/projection_network.py official repository ran no licence file found · pointer only · 2703adeb8c9b7fe3 · report
conv3x3 Junyi42/geoaware-sc/model_utils/projection_network.py official repository ran · our draft was wrong no licence file found · pointer only · dd1114865f06f0fd · report
convert_to_binary_mask Junyi42/geoaware-sc/utils/utils_correspondence.py official repository ran no licence file found · pointer only · 573379e424292b74 · report
get_activation Junyi42/geoaware-sc/model_utils/resnet.py official repository ran no licence file found · pointer only · ff7935588190c264 · report
get_logger Junyi42/geoaware-sc/utils/logger.py official repository ran no licence file found · pointer only · 0e22527aef7473f7 · report
get_norm Junyi42/geoaware-sc/model_utils/resnet.py official repository ran no licence file found · pointer only · 56e01a00f6319825 · report
load_config Junyi42/geoaware-sc/utils/logger.py official repository ran · our draft was wrong no licence file found · pointer only · e73d70bf254d0833 · report
log_weighted_pcks Junyi42/geoaware-sc/utils/logger.py official repository ran no licence file found · pointer only · b49f032c30dd19b3 · report
normalize_feats Junyi42/geoaware-sc/pck_train.py official repository ran no licence file found · pointer only · ff621aa7b96efd16 · report
preprocess_kps_pad Junyi42/geoaware-sc/preprocess_mask_sam.py official repository ran no licence file found · pointer only · 3df2b3119a2e453d · report
self_contrastive_loss Junyi42/geoaware-sc/utils/utils_losses.py official repository ran no licence file found · pointer only · 0eaf33937a382b3d · report
get_corr_map_loss Junyi42/geoaware-sc/utils/utils_losses.py official repository unverified no licence file found · pointer only · b93739dfc1daa1e0 · report
get_distance Junyi42/geoaware-sc/utils/utils_correspondence.py official repository unverified no licence file found · pointer only · 2c70990700a1be88 · report
get_distance_mutual_nn Junyi42/geoaware-sc/utils/utils_correspondence.py official repository unverified no licence file found · pointer only · 1cfa3d8da92fdbe1 · report
get_logits Junyi42/geoaware-sc/utils/utils_losses.py official repository unverified no licence file found · pointer only · 2bb017e5aba25a4a · report

Tasks

Animal Pose EstimationPose EstimationSemantic correspondence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic correspondence PF-PASCAL GeoAware-SC (Supervised, AP-10K P.T.) PCK 95.7 #2 of 15 Archive leaderboard report
Semantic correspondence PF-PASCAL GeoAware-SC (Supervised) PCK 95.1 #3 of 15 Archive leaderboard report
Semantic correspondence PF-PASCAL GeoAware-SC (Zero-Shot) PCK 82.6 #14 of 15 Archive leaderboard report
Semantic correspondence SPair-71k GeoAware-SC (Supervised, AP-10K P.T.) PCK 85.6 #1 of 22 Archive leaderboard report
Semantic correspondence SPair-71k GeoAware-SC (Supervised) PCK 82.9 #3 of 22 Archive leaderboard report
Semantic correspondence SPair-71k GeoAware-SC (Zero-Shot) PCK 68.5 #6 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.

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