REVIEW 14 cited by
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and accuracy, we proposed a practical ultra lightweight OCR system (PP-OCR), and an optimized version PP-OCRv2. In order to further improve the performance of PP-OCRv2, a more robust OCR system PP-OCRv3 is proposed in this paper. PP-OCRv3 upgrades the text detection model and text recognition model in 9 aspects based on PP-OCRv2. For text detector, we introduce a PAN module with large receptive field named LK-PAN, a FPN module with residual attention mechanism named RSE-FPN, and DML distillation strategy. For text recognizer, the base model is replaced from CRNN to SVTR, and we introduce lightweight text recognition network SVTR LCNet, guided training of CTC by attention, data augmentation strategy TextConAug, better pre-trained model by self-supervised TextRotNet, UDML, and UIM to accelerate the model and improve the effect. Experiments on real data show that the hmean of PP-OCRv3 is 5% higher than PP-OCRv2 under comparable inference speed. All the above mentioned models are open-sourced and the code is available in the GitHub repository PaddleOCR which is powered by PaddlePaddle.
Forward citations
Cited by 14 Pith papers
-
VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models
VTBench is a multi-dimensional benchmark with novel unpaired metrics and human preference data for evaluating image-based virtual try-on models, though the human-alignment evidence is incomplete.
-
Superbunched random fiber laser
A fiber-integrated random laser uses Rayleigh scattering, cascaded Brillouin scattering, and four-wave mixing to generate multi-wavelength superbunched light with g(2)(0) up to ~26 and improved temporal ghost imaging.
-
Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
A two-stage 'text-first, image-later' super-resolution framework restores glyph structures before enhancing the whole image, improving OCR accuracy and visual quality on a new extreme-zoom Chinese text dataset.
-
Uncertainty-Aware Complex Scientific Table Data Extraction
Applying conformal prediction to TSR+OCR outputs flags incorrect table cells; the paper reports 53% labor savings and a 30-point accuracy gain, but the flagging threshold is fitted to the test data.
-
FontAdapter: Instant Font Adaptation in Visual Text Generation
A two-stage curriculum with synthetic paired font data enables instant adaptation of unseen fonts in text-to-image generation using one reference glyph, without test-time fine-tuning.
-
OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
OCR-Reasoning, a 1,069-question benchmark with reasoning-chain annotations for text-rich images, finds that no evaluated multimodal model surpasses 50% accuracy.
-
SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation
SafeDrive228K is a 228K-example multimodal QA benchmark for traffic safety, and a graph-based RAG method improves VLM accuracy on it by 4.7 to 14.6 points across five models.
-
Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models
Classification-guided dynamic prompts improve zero-shot visual information extraction from 16 certificate types, reaching 86.43 F1 without LVLM fine-tuning on a private bidding dataset.
-
Interfaze: The Future of AI is built on Task-Specific Small Models
Interfaze-Beta uses small specialist models and tools to build a compact context that a general-purpose LLM answers from, reporting competitive benchmark scores without reproducible evidence.
-
E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition
Their custom PaddleOCR-based system achieves the best F1 (0.46), fastest latency (0.17 s/image), and lowest cost ($0.006/1k images) among seven OCR systems on a private 54-language benchmark.
-
TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition
A lightweight vision-language transformer with a weakly supervised perspective-correction module reaches about 99% accuracy on modified CCPD license plate benchmarks.
-
LPTR-AFLNet: Lightweight Integrated Chinese License Plate Rectification and Recognition Network
A lightweight integrated network with weak-supervised perspective rectification plus attention and Focal CTC loss improves Chinese license plate recognition speed and accuracy, including synthetic double-line plates.
-
Billet Number Recognition Based on Test-Time Adaptation
A test-time adaptation plus prior-knowledge correction method raises billet number recognition accuracy from 58% to 80% on machine-printed and from 24% to 70% on handwritten samples in the authors' tests.
-
Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR
Direct line-level recognition with PARSeq (trained on synthetic line images) beats word-level pipelines by 5.4% FCA and runs 4x faster on the authors' 251-page English dataset.
Discussion (0). Continue with ORCID to comment.