Papers › LINEA: Fast and Accurate Line Detection Using Scalable Transformers

LINEA: Fast and Accurate Line Detection Using Scalable Transformers

22 May 2025arXiv:2505.16264archive 2025-07-28

Sebastian Janampa, Marios Pattichis

Line detection is a basic digital image processing operation used by higher-level processing methods. Recently, transformer-based methods for line detection have proven to be more accurate than methods based on CNNs, at the expense of significantly lower inference speeds. As a result, video analysis methods that require low latencies cannot benefit from current transformer-based methods for line detection. In addition, current transformer-based models require pretraining attention mechanisms on large datasets (e.g., COCO or Object360). This paper develops a new transformer-based method that is significantly faster without requiring pretraining the attention mechanism on large datasets. We eliminate the need to pre-train the attention mechanism using a new mechanism, Deformable Line Attention (DLA). We use the term LINEA to refer to our new transformer-based method based on DLA. Extensive experiments show that LINEA is significantly faster and outperforms previous models on sAP in out-of-distribution dataset testing.

PaperPDFCode

Code

SebastianJanampa/LINEA officialmentioned in papermentioned 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Line DetectionLine Segment Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Line Segment Detection York Urban Dataset LINEA-L sAP10 34.9 #1 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-L sAP15 37.3 #1 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-L sAP5 30.9 #1 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-M sAP10 34.5 #2 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-M sAP15 36.7 #2 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-M sAP5 30.3 #2 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-S sAP10 32.6 #4 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-S sAP15 34.8 #4 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-S sAP5 28.9 #4 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-N sAP10 30.5 #8 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-N sAP15 32.5 #8 of 16 Archive leaderboard report
Line Segment Detection York Urban Dataset LINEA-N sAP5 27.3 #8 of 16 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

AttentionDLASoftmax

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