https://github.com/99franklin/difftext
공식 코드Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Scene Text Detection is a computer vision task that involves automatically identifying and localizing text within natural images or videos. The goal of scene text detection is to develop algorithms that can robustly detect and and label text with bounding boxes in uncontrolled and complex environments, such as street signs, billboards, or license plates.
Source: ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models
Vision-Language Pre-Training for Boosting Scene Text Detectors
SEE: Towards Semi-Supervised End-to-End Scene Text Recognition
STN-OCR: A single Neural Network for Text Detection and Text Recognition
MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild
DeRPN: Taking a further step toward more general object detection
UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
Real-time Scene Text Detection with Differentiable Binarization
SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
Omnidirectional Scene Text Detection with Sequential-free Box Discretization
Detecting Curve Text in the Wild: New Dataset and New Solution
Tightness-aware Evaluation Protocol for Scene Text Detection
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond
Moving Object Detection for Event-based vision using Graph Spectral Clustering
Geometry Normalization Networks for Accurate Scene Text Detection
ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
Text in the Dark: Extremely Low-Light Text Image Enhancement
Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition
FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
Weakly Supervised Scene Text Detection using Deep Reinforcement Learning
The First Swahili Language Scene Text Detection and Recognition Dataset
Recurrent Generic Contour-based Instance Segmentation with Progressive Learning
Towards End-to-End Unified Scene Text Detection and Layout Analysis
Arbitrary Shape Text Detection via Segmentation with Probability Maps
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.