Papers › EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition

EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition

21 Aug 2023ICCV 2023 1arXiv:2308.10832archive 2025-07-28

Gabriele Berton, Gabriele Trivigno, Barbara Caputo, Carlo Masone

Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, where the query is matched to the most similar images from a large database of geotagged photos, using learned global descriptors. A major challenge in this task is recognizing places seen from different viewpoints. To overcome this limitation, we propose a new method, called EigenPlaces, to train our neural network on images from different point of views, which embeds viewpoint robustness into the learned global descriptors. The underlying idea is to cluster the training data so as to explicitly present the model with different views of the same points of interest. The selection of this points of interest is done without the need for extra supervision. We then present experiments on the most comprehensive set of datasets in literature, finding that EigenPlaces is able to outperform previous state of the art on the majority of datasets, while requiring 60\% less GPU memory for training and using 50\% smaller descriptors. The code and trained models for EigenPlaces are available at {\small{\url{https://github.com/gmberton/EigenPlaces}}}, while results with any other baseline can be computed with the codebase at {\small{\url{https://github.com/gmberton/auto_VPR}}}.

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="2308.10832")

Code

Syntology Ran 11 of 13 code samples harvested from 3 repositories linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 12 samples from 2 repositories, 11 ran; community (archive-listed): 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gmberton/auto_vpr officialmentioned in papermentioned on GitHubpytorchMIT report
gmberton/eigenplaces officialmentioned in papermentioned on GitHubpytorchMIT report
gmberton/VPR-methods-evaluation mentioned on GitHubpytorchMIT report
stschubert/vpr_tutorial mentioned 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

13 samples harvested; 11 ran; 0 honoured the contract we drafted; 2 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.

3ran · our draft was wrong
8ran
2unverified

Licence: 1 of the 13 samples is 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

FeatureMixerLayer gmberton/auto_VPR/vpr_models/mixvpr.py official repository ran · metamorphic tier: deterministic MIT (permissive) · b1d538a389832e87 · report
GeoLocalizationNet_ gmberton/EigenPlaces/eigenplaces_model/eigenplaces_network.py official repository ran fingerprinted MIT (permissive) · 8b7f9cc4b0bc470c · report
MixVPR gmberton/auto_VPR/vpr_models/mixvpr.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 484d075328eb2fed · report
_get_backbone gmberton/EigenPlaces/eigenplaces_model/eigenplaces_network.py official repository ran · our draft was wrong MIT (permissive) · ff1c204640bf5d26 · report
_get_torchvision_model gmberton/EigenPlaces/eigenplaces_model/eigenplaces_network.py official repository ran · our draft was wrong MIT (permissive) · 67c4edb815d13c58 · report
gem gmberton/eigenplaces/eigenplaces_model/layers.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 79f68aea8273d062 · report
get_angle gmberton/eigenplaces/datasets/eigenplaces_dataset.py official repository ran fingerprinted MIT (permissive) · c9a712e4ab767554 · report
get_edges gmberton/eigenplaces/datasets/map_utils.py official repository ran MIT (permissive) · 5c494b746f3224d0 · report
get_eigen_things gmberton/eigenplaces/datasets/eigenplaces_dataset.py official repository ran fingerprinted MIT (permissive) · 1bdc886968023e1f · report
read_images_paths gmberton/eigenplaces/datasets/dataset_utils.py official repository ran MIT (permissive) · 9eb0e8b7020e7e45 · report
rotate_2d_vector gmberton/eigenplaces/datasets/eigenplaces_dataset.py official repository ran MIT (permissive) · ea694f879e5b5e72 · report
cosine_sim gmberton/eigenplaces/cosface_loss.py official repository unverified MIT (permissive) · d7ebec9a9c0c9b14 · report
EigenPlacesFeatureExtractor stschubert/vpr_tutorial/feature_extraction/feature_extractor_eigenplaces.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 6f419867237c7d74 · report

Tasks

Image RetrievalRetrievalVisual Place Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Place Recognition AmsterTime EigenPlaces Recall@1 48.9 #8 of 8 Archive leaderboard report
Visual Place Recognition Eynsham EigenPlaces Recall@1 90.7 #7 of 7 Archive leaderboard report
Visual Place Recognition Pittsburgh-250k-test EigenPlaces Recall@1 94.1 #9 of 13 Archive leaderboard report
Visual Place Recognition Pittsburgh-30k-test EigenPlaces Recall@1 92.5 #11 of 22 Archive leaderboard report
Visual Place Recognition SF-XL test v1 EigenPlaces Recall@1 84.1 #4 of 5 Archive leaderboard report
Visual Place Recognition SF-XL test v2 EigenPlaces Recall@1 90.8 #4 of 5 Archive leaderboard report
Visual Place Recognition SF-XL test v2 EigenPlaces Recall@10 96.7 #4 of 5 Archive leaderboard report
Visual Place Recognition SF-XL test v2 EigenPlaces Recall@5 95.7 #4 of 5 Archive leaderboard report
Visual Place Recognition San Francisco Landmark Dataset EigenPlaces Recall@1 89.6 #3 of 3 Archive leaderboard report
Visual Place Recognition Tokyo247 EigenPlaces Recall@1 93 #9 of 14 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