SymPoint Revolutionized: Boosting Panoptic Symbol Spotting with Layer Feature Enhancement
This work addresses a domain-specific problem in CAD drawing analysis, offering incremental improvements for researchers and practitioners in computer vision and design automation.
The paper tackles the problem of slow training convergence and overlooked graphical layer information in panoptic symbol spotting on CAD drawings by introducing SymPoint-V2 with a Layer Feature-Enhanced module and Position-Guided Training method, achieving better performance and faster convergence than the previous SymPoint model.
SymPoint is an initial attempt that utilizes point set representation to solve the panoptic symbol spotting task on CAD drawing. Despite its considerable success, it overlooks graphical layer information and suffers from prohibitively slow training convergence. To tackle this issue, we introduce SymPoint-V2, a robust and efficient solution featuring novel, streamlined designs that overcome these limitations. In particular, we first propose a Layer Feature-Enhanced module (LFE) to encode the graphical layer information into the primitive feature, which significantly boosts the performance. We also design a Position-Guided Training (PGT) method to make it easier to learn, which accelerates the convergence of the model in the early stages and further promotes performance. Extensive experiments show that our model achieves better performance and faster convergence than its predecessor SymPoint on the public benchmark. Our code and trained models are available at https://github.com/nicehuster/SymPointV2.