Papers › LATR: 3D Lane Detection from Monocular Images with Transformer

LATR: 3D Lane Detection from Monocular Images with Transformer

8 Aug 2023ICCV 2023 1arXiv:2308.04583archive 2025-07-28

Yueru Luo, Chaoda Zheng, Xu Yan, Tang Kun, Chao Zheng, Shuguang Cui, Zhen Li

3D lane detection from monocular images is a fundamental yet challenging task in autonomous driving. Recent advances primarily rely on structural 3D surrogates (e.g., bird's eye view) built from front-view image features and camera parameters. However, the depth ambiguity in monocular images inevitably causes misalignment between the constructed surrogate feature map and the original image, posing a great challenge for accurate lane detection. To address the above issue, we present a novel LATR model, an end-to-end 3D lane detector that uses 3D-aware front-view features without transformed view representation. Specifically, LATR detects 3D lanes via cross-attention based on query and key-value pairs, constructed using our lane-aware query generator and dynamic 3D ground positional embedding. On the one hand, each query is generated based on 2D lane-aware features and adopts a hybrid embedding to enhance lane information. On the other hand, 3D space information is injected as positional embedding from an iteratively-updated 3D ground plane. LATR outperforms previous state-of-the-art methods on both synthetic Apollo, realistic OpenLane and ONCE-3DLanes by large margins (e.g., 11.4 gain in terms of F1 score on OpenLane). Code will be released at https://github.com/JMoonr/LATR .

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="2308.04583")

Code

Syntology Ran 11 of 14 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 10 ran with no contract checked.

By repository: official repository: 14 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.

jmoonr/latr officialmentioned in papermentioned on GitHubpytorchMIT 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

14 samples harvested; 11 ran; 0 honoured the contract we drafted; 3 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 · our draft was wrong
10ran
3unverified

Licence: 0 of the 14 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 JMoonr/LATR. “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.

aligned_bilinear JMoonr/LATR/models/sparse_inst_loss.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 29dbbaafa4be18e1 · report
build_ms2one JMoonr/LATR/models/ms2one.py official repository ran MIT (permissive) · deccd45b122f35df · report
build_nn_loss JMoonr/LATR/models/latr_head.py official repository ran MIT (permissive) · 4c0969530211fe04 · report
inverse_sigmoid JMoonr/LATR/models/utils.py official repository ran fingerprinted MIT (permissive) · c12fa9dce0d5fd34 · report
nested_masks_from_list JMoonr/LATR/models/sparse_inst_loss.py official repository ran MIT (permissive) · 70f2a7785acb5193 · report
nested_tensor_from_tensor_list JMoonr/LATR/models/sparse_inst_loss.py official repository ran MIT (permissive) · e0e4b133a453e3c3 · report
pos2posemb3d JMoonr/LATR/models/transformer_bricks.py official repository ran fingerprinted MIT (permissive) · 615e86e6f80e97ba · report
reduce_tensor JMoonr/LATR/experiments/ddp.py official repository ran MIT (permissive) · be5abd3083ea4db8 · report
scatter_add JMoonr/LATR/models/scatter_utils.py official repository ran MIT (permissive) · e2d07b9f31178c8b · report
scatter_sum JMoonr/LATR/models/scatter_utils.py official repository ran MIT (permissive) · db8f88398b43049d · report
to_python_float JMoonr/LATR/experiments/ddp.py official repository ran MIT (permissive) · 6b5d363ab4dbf012 · report
broadcast JMoonr/LATR/models/scatter_utils.py official repository unverified MIT (permissive) · 5dd38da29766376b · report
generate_ref_pt JMoonr/LATR/models/transformer_bricks.py official repository unverified MIT (permissive) · 190869ab9960b5ad · report
ground2img JMoonr/LATR/models/transformer_bricks.py official repository unverified MIT (permissive) · 2d041f7c6096d5d9 · report

Tasks

3D Lane DetectionAutonomous DrivingLane Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Lane Detection OpenLane LATR Curve 68.2 #5 of 21 Archive leaderboard report
3D Lane Detection OpenLane LATR Extreme Weather 57.1 #5 of 21 Archive leaderboard report
3D Lane Detection OpenLane LATR F1 (all) 61.9 #5 of 21 Archive leaderboard report
3D Lane Detection OpenLane LATR Intersection 52.3 #5 of 21 Archive leaderboard report
3D Lane Detection OpenLane LATR Merge & Split 61.5 #5 of 21 Archive leaderboard report
3D Lane Detection OpenLane LATR Night 55.4 #5 of 21 Archive leaderboard report
3D Lane Detection OpenLane LATR Up & Down 55.2 #5 of 21 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

Apollo

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