Modelpublic

beclab/PP-DocLayoutV3_onnx

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

1likes26downloads

Model Card

Unified Layout Module for PaddleOCR-VL 1.5/1.6 & GLM-OCR

</h1>

![repo](https://github.com/PaddlePaddle/PaddleOCR) ![HuggingFace](https://huggingface.co/PaddlePaddle/PP-DocLayoutV3) ![ModelScope](https://modelscope.cn/models/PaddlePaddle/PP-DocLayoutV3) ![HuggingFace](https://huggingface.co/spaces/PaddlePaddle/PaddleOCR-VL-1.5OnlineDemo) ![ModelScope](https://modelscope.cn/studios/PaddlePaddle/PaddleOCR-VL-1.5OnlineDemo/summary) ![Discord](https://discord.gg/JPmZXDsEEK) ![X](https://x.com/PaddlePaddle) ![License](./LICENSE)

🔥 [Official Website](https://www.paddleocr.com) | 📝 [Technical Report](https://arxiv.org/abs/2606.23344)

</div>

Introduction

This is the model weights for PP-DocLayoutv3 in safetensors format. Get PaddlePaddle weights at PP-DocLayoutV3

PP-DocLayoutV3 is specifically engineered to handle non-planar document images. It can directly predict multi-point bounding boxes for layout elements—as opposed to standard two-point boxes—and determine logical reading orders for skewed and curved surfaces within a single forward pass, significantly reducing cascading errors. This model is an essential component of PaddleOCR-VL-1.5, providing crucial layout analysis for the high-precision parsing of various real-world documents in PaddleOCR-VL.

This work has been accepted to ECCV 2026! 🎉

Model Architecture

Model Usage

python

import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForObjectDetection

model_path = "PaddlePaddle/PP-DocLayoutV3_safetensors"
model = AutoModelForObjectDetection.from_pretrained(model_path)
image_processor = AutoImageProcessor.from_pretrained(model_path)

image = Image.open(requests.get("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout_demo.jpg", stream=True).raw)
inputs = image_processor(images=image, return_tensors="pt")

outputs = model(**inputs)
results = image_processor.post_process_object_detection(outputs, target_sizes=[image.size[::-1]])
for result in results:
    for idx, (score, label_id, box, polygon_points) in enumerate(zip(result["scores"], result["labels"], result["boxes"], result["polygon_points"])):
        score, label = score.item(), label_id.item()
        box = [round(i, 2) for i in box.tolist()]
        print(f"Order {idx + 1}: {model.config.id2label[label]}, score: {score:.2f}, box: {box}, polygon_points: {polygon_points}")

Visualization

Light Variation

Skewing

Screen-photo

Curving

Citation

If you find PP-DocLayoutV3 helpful, feel free to give us a star and citation.

bibtex

@misc{cui2026rtdoclayoutrealtimeendtoenddocument,
      title={RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild}, 
      author={Cheng Cui and Tingquan Gao and Xueqing Wang and Changda Zhou and Hongen Liu and Ting Sun and Yubo Zhang and Zelun Zhang and Jiaxuan Liu and Manhui Lin and Yue Zhang and Suyin Liang and Yiqing Xiang and Yi Liu},
      year={2026},
      eprint={2606.23344},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2606.23344}, 
}
}