PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
This work addresses the problem of handling distorted documents for applications like OCR and document analysis, though it appears incremental as an upgrade to an existing model.
The paper tackles robust document parsing in real-world conditions by introducing PaddleOCR-VL-1.5, which achieves a new state-of-the-art accuracy of 94.5% on OmniDocBench v1.5 and demonstrates strong performance on a new benchmark for physical distortions.
We introduce PaddleOCR-VL-1.5, an upgraded model achieving a new state-of-the-art (SOTA) accuracy of 94.5% on OmniDocBench v1.5. To rigorously evaluate robustness against real-world physical distortions, including scanning, skew, warping, screen-photography, and illumination, we propose the Real5-OmniDocBench benchmark. Experimental results demonstrate that this enhanced model attains SOTA performance on the newly curated benchmark. Furthermore, we extend the model's capabilities by incorporating seal recognition and text spotting tasks, while remaining a 0.9B ultra-compact VLM with high efficiency. Code: https://github.com/PaddlePaddle/PaddleOCR