README.md

metadata

title: ArmorOCR
emoji: 🛡️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 6.29.1
app_file: app.py
short_description: Grounded adversarial OCR perception with ArmorOCR
python_version: '3.10'
startup_duration_timeout: 30m
license: apache-2.0

ArmorOCR: Grounded Adversarial OCR

Demo of inclusionAI/ArmorOCR, a Qwen3-VL-8B-Instruct finetune for grounded adversarial OCR perception — recognizing text that is hard even for humans to spot at a glance: low-contrast blends, dot/line encodings, dense pattern overlays, tiny or stylized text, and more.

The app runs single-pass inference on the original image (no inference-time visual transformations) in two modes:

• Grounded spotting — recognizes the hidden text and localizes it with a bounding box (0–1000 normalized coordinates), drawn on the image.
• Free-form prompt — ask any question about the text in the image, using the official <analyze>/<answer> prompt template.

Example images are taken from the official ant-research/ArmorOCR repository (Apache-2.0).

• 📄 Paper: ArmorOCR: Grounded Adversarial Visual Perception via Observation-Transferred Self-Distillation
• 💻 Code: ant-research/ArmorOCR
• 🤗 Model: inclusionAI/ArmorOCR · GGUF: inclusionAI/ArmorOCR-GGUF
• 🤗 Benchmark: inclusionAI/advspot-public

License: Apache License 2.0.