Methods › Computer Vision › RoI Feature Extractors › BezierAlign
BezierAlign
Introduced by Yuliang Liu et al. in ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
BezierAlign is a feature sampling method for arbitrarily-shaped scene text recognition that exploits parameterization nature of a compact Bezier curve bounding box. Unlike RoIAlign, the shape of sampling grid of BezierAlign is not rectangular. Instead, each column of the arbitrarily-shaped grid is orthogonal to the Bezier curve boundary of the text. The sampling points have equidistant interval in width and height, respectively, which are bilinear interpolated with respect to the coordinates.
Formally given an input feature map and Bezier curve control points, we concurrently process all the output pixels of the rectangular output feature map with size hₒᵤₜ ×wₒᵤₜ. Taking pixel gᵢ with position (g_(i w), g_(i h)) (from output feature map) as an example, we calculate t by:
t=(g_(i w))/(w_(o u t))
We then calculate the point of upper Bezier curve boundary tp and lower Bezier curve boundary bp. Using tp and bp, we can linearly index the sampling point op by:
op=bp ·(g_(i h))/hₒᵤₜ+tp ·(1-(g_(i h))/hₒᵤₜ)
With the position of op, we can easily apply bilinear interpolation to calculate the result. Comparisons among previous sampling methods and BezierAlign are shown in the Figure.
Papers archive 2025-07-28
3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting 8 May 2021 · 1 repository · arXiv:2105.03620
-
DocBank: A Benchmark Dataset for Document Layout Analysis 1 Jun 2020 · 2 repositories · arXiv:2006.01038
-
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network 24 Feb 2020 · 16 repositories · arXiv:2002.10200Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Text Spotting | 2 |
| Document Layout Analysis | 1 |
| Scene Text Detection | 1 |
| Text Detection | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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