Realistic Compound-Lens Defocus Blur Synthesis
For researchers in image deblurring, this work addresses the lack of diverse and realistic training data that limits cross-device generalization of deep learning methods.
The paper proposes a pipeline for synthesizing realistic defocus blur datasets for compound lenses, enabling scalable generation of photorealistic defocus image pairs. Models trained on the resulting CLDefocus dataset achieve improved cross-device generalization compared to those trained on existing datasets.
Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learning deblurring methods have achieved strong performance, their effectiveness depends on training data and often degrades across cameras and lenses due to limited optical diversity and realism in existing datasets. In this paper, we propose a pipeline for synthesizing realistic defocus deblurring datasets for diverse compound lenses. It integrates efficient wave-optics PSF computation via Debye CZT propagation, depth-aware defocus rendering with occlusion handling, and blur synthesis in the radiometrically linear space with camera ISP simulation. This unified pipeline enables the scalable generation of photorealistic defocus datasets with diverse lens characteristics. Using our pipeline, we generate CLDefocus, a large-scale synthetic dataset containing lens-diverse defocus image pairs. We further analyze the limitations of real-captured defocus datasets and show that such imperfections can bias full-reference evaluation. Extensive experiments demonstrate that models trained on CLDefocus achieve improved cross-device generalization compared to models trained on existing real and synthetic datasets.