Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild
Keywords:CV: Low Level & Physics-Based Vision, CV: 3D Computer Vision, CV: Applications, CV: Computational Photography, Image & Video Synthesis
AbstractRecent research showed that the dual-pixel sensor has made great progress in defocus map estimation and image defocus deblurring. However, extracting real-time dual-pixel views is troublesome and complex in algorithm deployment. Moreover, the deblurred image generated by the defocus deblurring network lacks high-frequency details, which is unsatisfactory in human perception. To overcome this issue, we propose a novel defocus deblurring method that uses the guidance of the defocus map to implement image deblurring. The proposed method consists of a learnable blur kernel to estimate the defocus map, which is an unsupervised method, and a single-image defocus deblurring generative adversarial network (DefocusGAN) for the first time. The proposed network can learn the deblurring of different regions and recover realistic details. We propose a defocus adversarial loss to guide this training process. Competitive experimental results confirm that with a learnable blur kernel, the generated defocus map can achieve results comparable to supervised methods. In the single-image defocus deblurring task, the proposed method achieves state-of-the-art results, especially significant improvements in perceptual quality, where PSNR reaches 25.56 dB and LPIPS reaches 0.111.
How to Cite
Zhai, J., Zeng, P., Ma, C., Chen, J., & Zhao, Y. (2023). Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3384-3392. https://doi.org/10.1609/aaai.v37i3.25446
AAAI Technical Track on Computer Vision III