Alternatives and similar repositories for PSTR

Users that are interested in PSTR are comparing it to the libraries listed below

• mxin262 / Bridging-Text-Spotting
  (CVPR 2024) Bridging the Gap Between End-to-End and Two-Step Text Spotting.
  ☆66Updated last year
• mxin262 / ESTextSpotter
  (ICCV 2023) ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer
  ☆77Updated last year
• SCUT-DLVCLab / OCR-Reasoning
  [arXiv: 2505.17163] OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
  ☆60Updated last week
• caipeng328 / ForCenNet
  ☆31Updated last week
• retsuh-bqw / SRFormer-Text-Det
  [AAAI 2024] SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression
  ☆66Updated 5 months ago
• bytedance / E2STR
  The official code for the CVPR 2024 paper: Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer
  ☆53Updated last year
• whai362 / pan_pp_stable
  ☆28Updated 2 years ago
• xdxie / WordArt
  The official code of CornerTransformer (ECCV 2022, Oral) on top of MMOCR.
  ☆145Updated 2 years ago
• PriNing / ODM
  ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
  ☆41Updated 4 months ago
• SCUT-DLVCLab / MegaHan97K
  [PR 2025] The official GitHub page of "MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Ca…
  ☆62Updated 3 weeks ago
• Mountchicken / Union14M
  [ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective
  ☆190Updated last year
• wenwenyu / TCM
  Turning a CLIP Model into a Scene Text Detector (CVPR2023) | Turning a CLIP Model into a Scene Text Spotter (TPAMI)
  ☆193Updated last year
• weijiawu / TransDETR
  [IJCV 2024] TransDETR: End-to-end Video Text Spotting with Transformer
  ☆104Updated last year
• ThunderVVV / RCLSTR
  Official PyTorch implementation of `[ACMMM 2023]Relational Contrastive Learning for Scene Text Recognition`
  ☆17Updated last year
• shannanyinxiang / SPTS
  Official implementation of SPTS: Single-Point Text Spotting (ACM MM 2022 Oral)
  ☆143Updated 2 years ago
• bytedance / SPTSv2
  The official implementation of SPTS v2: Single-Point Text Spotting
  ☆136Updated 2 years ago
• fh2019ustc / DeepEraser
  The official code for “DeepEraser: Deep Iterative Context Mining for Generic Text Eraser”, TMM, 2024.
  ☆42Updated 11 months ago
• SCUT-DLVCLab / SCUT-EnsExam
  SCUT-EnsExam is a real-world handwritten text erasure dataset for examination paper scenarios, which consists of 545 examination paper im…
  ☆13Updated last year
• yufanchen96 / RoDLA
  RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
  ☆36Updated 4 months ago
• Hxyz-123 / GoMatching
  [NeurIPS'24] GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
  ☆26Updated 2 months ago
• SCUT-DLVCLab / GPT-4V_OCR
  Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)
  ☆125Updated last year
• Token-family / TokenFD
  [ICCV2025] A Token-level Text Image Foundation Model for Document Understanding
  ☆111Updated last week
• yyyyyxie / DNTextSpotter
  [ACMMM 2024]: Official implementation of the paper "DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training"
  ☆30Updated 9 months ago
• zzyhlyoko / DCTC
  ☆42Updated last year
• lcy0604 / CTRNet
  This repository is the implementation of "Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Contex…
  ☆87Updated 2 years ago
• ymy-k / DPText-DETR
  [AAAI'23 Oral] DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
  ☆191Updated last year
• large-ocr-model / large-ocr-model.github.io
  ☆181Updated last year
• yh-hust / PDF-Wukong
  【ArXiv】PDF-Wukong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling
  ☆122Updated 2 months ago
• Wei-ucas / TPSNet
  ☆26Updated last year
• mlpc-ucsd / TESTR
  (CVPR 2022) Text Spotting Transformers
  ☆187Updated 2 years ago