Iterative Filter Adaptive Network for Single Image Defocus Deblurring

Abstract

We propose a novel end-to-end learning-based approach for single image defocus deblurring. The proposed approach is equipped with a novel Iterative Filter Adaptive Network (IFAN) that is specifically designed to handle spatially-varying and large defocus blur. For adaptively handling spatially-varying blur, IFAN predicts pixel-wise deblurring filters, which are applied to defocused features of an input image to generate deblurred features. For effectively managing large blur, IFAN models deblurring filters as stacks of small-sized separable filters. Predicted separable deblurring filters are applied to defocused features using a novel Iterative Adaptive Convolution (IAC) layer. We also propose a training scheme based on defocus disparity estimation and reblurring, which significantly boosts the deblurring quality. We demonstrate that our method achieves state-of-the-art performance both quantitatively and qualitatively on real-world images.

CVPR 2021

Cited by in corpus (13)

• Restormer: Efficient Transformer for High-Resolution Image Restoration
• Depth Estimation and Image Restoration by Deep Learning from Defocused Images
• Gaussian Kernel Mixture Network for Single Image Defocus Deblurring
• DMTNet: Dynamic Multi-scale Network for Dual-pixel Images Defocus Deblurring with Transformer
• Real-Time Video Deblurring via Lightweight Motion Compensation
• Towards Context-aware Convolutional Network for Image Restoration
• Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair
• Dual-Camera All-in-Focus Neural Radiance Fields
• Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
• Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network
• Deblur-NeRF: Neural Radiance Fields from Blurry Images
• Learning to Refocus with Video Diffusion Models
• Adjust Your Focus: Defocus Deblurring From Dual-Pixel Images Using Explicit Multi-Scale Cross-Correlation