Papers › EAST: An Efficient and Accurate Scene Text Detector

EAST: An Efficient and Accurate Scene Text Detector

11 Apr 2017CVPR 2017 7arXiv:1704.03155archive 2025-07-28

Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, Jiajun Liang

Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines. In this work, we propose a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes. The pipeline directly predicts words or text lines of arbitrary orientations and quadrilateral shapes in full images, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning), with a single neural network. The simplicity of our pipeline allows concentrating efforts on designing loss functions and neural network architecture. Experiments on standard datasets including ICDAR 2015, COCO-Text and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency. On the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.7820 at 13.2fps at 720p resolution.

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="1704.03155")

Code

Syntology Ran 5 of 6 code samples harvested from 4 repositories linked to this paper; 1 has no recorded run. Of those that ran: 3 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 6 samples from 4 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

31 repositories listed; official and paper-mentioned ones first.

CCLDArjun/Arjun-EAST mentioned on GitHubpytorch report
Chris10M/RFB-Text-Detection mentioned on GitHubtf report
GokulKarthik/EAST.pytorch mentioned on GitHubpytorch report
Kaushal28/FOTS-PyTorch mentioned on GitHubpytorch report
Mind23-2/MindCode-35 mentioned on GitHubmindspore report
PaddlePaddle/PaddleOCR mentioned on GitHubpaddleApache-2.0 report
alililia/ascend_advanced_east mentioned on GitHubmindspore report
argman/EAST mentioned on GitHubtf report
dengdan/seglink mentioned on GitHubtf report
ingbeeedd/EAST-tf2keras mentioned on GitHubtf report
isaacaddis/Seung mentioned on GitHub report
jnkl314/tin_dr mentioned on GitHub report
kurapan/EAST mentioned on GitHubtf report
liushuchun/EAST.pytorch mentioned on GitHubpytorch report
solaris33/EAST-tf2 mentioned on GitHubtf report
swapnamoy17/EAST-DenseNet mentioned on GitHubtf report
yakhyo/east-pytorch mentioned on GitHubpytorch report
zxytim/EAST mentioned on GitHubtf report
zyasjtu/EAST mentioned on GitHubtf report
mindspore-lab/mindocr mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready 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

6 samples harvested; 5 ran; 0 honoured the contract we drafted; 1 has 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
2ran · fixture could not drive it
1unverified

Licence: 1 of the 6 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 4 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.

get_path_list Chris10M/RFB-Text-Detection/run_demo.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 2810b57a93d7c863 · report
is_valid_poly yakhyo/east-pytorch/detect.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · d683e0b7226e6e35 · report
is_valid_poly SakuraRiven/EAST/detect.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 66e30af743cc4a1a · report
resize yakhyo/east-pytorch/detect.py community (archive-listed) ran · our draft was wrong MIT (permissive) · e55b33eadf6b16e5 · report
resize_img SakuraRiven/EAST/detect.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 31e0255b8c515ebb · report
get_predictor argman/EAST/run_demo_server.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 85d1fadaaf9cb100 · report

Tasks

Curved Text DetectionOptical Character Recognition (OCR)Scene Text DetectionText Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection COCO-Text EAST + VGG16 F-Measure 39.45 #3 of 6 Archive leaderboard report
Scene Text Detection COCO-Text EAST + VGG16 Precision 50.39 #3 of 6 Archive leaderboard report
Scene Text Detection COCO-Text EAST + VGG16 Recall 32.4 #3 of 6 Archive leaderboard report
Scene Text Detection ICDAR 2015 PAN F-Measure 82.9 #33 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 PAN Precision 84 #33 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 PAN Recall 81.9 #33 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 EAST + PVANET2x RBOX (single-scale) F-Measure 78.2 #37 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 EAST + PVANET2x RBOX (single-scale) Precision 83.6 #37 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 EAST + PVANET2x RBOX (single-scale) Recall 73.5 #37 of 43 Archive leaderboard report
Scene Text Detection MSRA-TD500 EAST + PVANET2x F-Measure 76.08 #18 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 EAST + PVANET2x Precision 87.28 #18 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 EAST + PVANET2x Recall 67.43 #18 of 18 Archive leaderboard report
Scene Text Detection Total-Text EAST F-Measure 42.0% #26 of 27 Archive leaderboard report
Scene Text Detection Total-Text EAST Precision 50.0 #26 of 27 Archive leaderboard report
Scene Text Detection Total-Text EAST Recall 36.2 #26 of 27 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