Papers › D2-Net: A Trainable CNN for Joint Detection and Description of Local Features

D2-Net: A Trainable CNN for Joint Detection and Description of Local Features

9 May 2019arXiv:1905.03561archive 2025-07-28

Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler

In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector. By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counterparts based on early detection of low-level structures. We show that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any further annotations. The proposed method obtains state-of-the-art performance on both the difficult Aachen Day-Night localization dataset and the InLoc indoor localization benchmark, as well as competitive performance on other benchmarks for image matching and 3D reconstruction.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (mihaidusmanu/d2-net) was not harvested; the 13 samples below come from 2 community repositories.

Syntology 13 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 13 samples from 2 repositories, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mihaidusmanu/d2-net officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
UditSinghParihar/d2-net mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
naver/kapture mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robust Image Retrieval-based Visual Localization using Kapture (arXiv:2007.13867; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
visinf/cad mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 4 ran (0 instrument-failed) · 8 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

13 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
4ran
8unverified

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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

UditSinghParihar/d2-net community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
readCSV evaluate/evalVPR.py ran · our draft was wrong licence not identified · pointer only · 53433044260a41dc · report fixture: signature file:str/0/str · returned list · level recorded 2026-09-22
visinf/cad community (archive-listed) 12 samples, 4 ran (0 instrument-failed) · 8 unverified
b_imresize segmentation/network/learned_mask.py ran Apache-2.0 (permissive) · bf609f8b8ca5b7c1 · report fixture: signature im:Tensor/4/float, size:tuple/1/int, interp:str/0/str · returned Tensor · level recorded 2026-09-24
fast_resize segmentation/network/learned_mask.py ran fingerprinted Apache-2.0 (permissive) · 3df35726b6ee41b5 · report fixture: signature im:Tensor/4/float, skips:int/0/int · returned Tensor · level recorded 2026-09-24
validate in 313 papers segmentation/main_e2e_eval.py ran Apache-2.0 (permissive) · 9e30645433461d06 · report fixture: signature opts:dict/0/?, model:callable/0/?, model_debug:callable/0/?, loader:list/1/tuple, device:str/0/str, metrics:Metrics/0/?, metrics_debug:Metrics/0/? · returned tuple · level recorded 2026-09-24
validate in 313 papers segmentation/main_e2e_train.py ran Apache-2.0 (permissive) · 674566c31ffc6904 · report fixture: signature opts:MinimalOpts/0/?, model:callable/0/?, loader:list/1/tuple, device:str/0/str, metrics:MinimalMetrics/0/?, ret_samples_ids:NoneType/0/?, activation:dict/0/?, criterion:callable/0/? · returned tuple · level recorded 2026-09-24
convert_to_separable_conv in 11 papers segmentation/network/_deeplab.py unverified Apache-2.0 (permissive) · ce942a958c0ae909 · report
create_grid in 10 papers segmentation/network/learned_mask.py unverified Apache-2.0 (permissive) · 271cada3b4e82e8d · report
deeplabv3_ad_resnet101 segmentation/network/modeling_e2e.py unverified Apache-2.0 (permissive) · 2ed438154419b053 · report
deeplabv3_ap_resnet50 segmentation/network/modeling.py unverified Apache-2.0 (permissive) · eca45a1c6dd6c659 · report
deeplabv3_batch_ap_resnet50 segmentation/network/modeling.py unverified Apache-2.0 (permissive) · a457e779f0591a28 · report
deeplabv3_resnet101 in 5 papers segmentation/network/modeling_e2e.py unverified Apache-2.0 (permissive) · 1c1ab9e04754c160 · report
deeplabv3_resnet50 in 7 papers segmentation/network/modeling.py unverified Apache-2.0 (permissive) · 451fc815fe699edb · report
deeplabv3_resnet50 in 7 papers segmentation/network/modeling_e2e.py unverified Apache-2.0 (permissive) · 909a6da223d37612 · report

Tasks

3D ReconstructionImage MatchingIndoor Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Matching IMC PhotoTourism D2-Net (MS) mean average accuracy @ 10 0.36285 #8 of 8 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