Cascades of Regression Tree Fields for Image Restoration

Abstract

Conditional random fields (CRFs) are popular discriminative models for computer vision and have been successfully applied in the domain of image restoration, especially to image denoising. For image deblurring, however, discriminative approaches have been mostly lacking. We posit two reasons for this: First, the blur kernel is often only known at test time, requiring any discriminative approach to cope with considerable variability. Second, given this variability it is quite difficult to construct suitable features for discriminative prediction. To address these challenges we first show a connection between common half-quadratic inference for generative image priors and Gaussian CRFs. Based on this analysis, we then propose a cascade model for image restoration that consists of a Gaussian CRF at each stage. Each stage of our cascade is semi-parametric, i.e. it depends on the instance-specific parameters of the restoration problem, such as the blur kernel. We train our model by loss minimization with synthetically generated training data. Our experiments show that when applied to non-blind image deblurring, the proposed approach is efficient and yields state-of-the-art restoration quality on images corrupted with synthetic and real blur. Moreover, we demonstrate its suitability for image denoising, where we achieve competitive results for grayscale and color images.

Submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence

References in corpus (1)

• Revisiting loss-specific training of filter-based MRFs for image restoration

Cited by in corpus (8)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Learning Converged Propagations with Deep Prior Ensemble for Image Enhancement
• INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions
• Deep Gaussian Conditional Random Field Network: A Model-based Deep Network for Discriminative Denoising
• Learning Deep Gradient Descent Optimization for Image Deconvolution
• Simultaneous Fidelity and Regularization Learning for Image Restoration
• DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring
• Learning Discriminative Shrinkage Deep Networks for Image Deconvolution