Category-Specific Object Image Denoising

Abstract

We present a novel image denoising algorithm that uses external, category specific image database. In contrast to existing noisy image restoration algorithms that search patches either from a generic database or noisy image itself, our method first selects clean images similar to the noisy image from a database that consists of images of the same class. Then, within the spatial locality of each noisy patch, it assembles a set of "support patches" from the selected images. These noisy-free support samples resemble the noisy patch and correspond principally to the identical part of the depicted object. In addition, we employ a content adaptive distribution model for each patch, where we derive the parameters of the distribution from the support patches. We formulate noise removal task as an optimization problem in the transform domain. Our objective function composed of a Gaussian fidelity term that imposes category specific information, and a low-rank term that encourages the similarity between the noisy and the support patches in a robust manner. The denoising process is driven by an iterative selection of support patches and optimization of the objective function. Our extensive experiments on five different object categories confirm the benefit of incorporating category-specific information to noise removal and demonstrate the superior performance of our method over the state-of-the-art alternatives.

HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment

“…However, most existing methods for general natural images are still sensitive to the degradation profile [9] and exhibit poor generalization over unconstrained testing conditions. For category-specific [2] (face) restoration, it is commonly believed that incorporating external guidance on facial prior would boost the restoration performance, such as semantic prior [38], identity prior [12], facial landmarks [4] [5] or component heatmaps [60]. In particular, Li et.al.…”

“…When it comes to blind image restoration [44], researchers aim to recover high-quality images from their degraded observation in a "single-blind" manner without a priori knowledge about the type and intensity of the degradation. It is often challenging to reconstruct image contents from artifacts without degradation prior, necessitating additional guidance information such as categorial [2] or structural prior [5] to facilitate the replenishment of faithful and photo-realistic details. For blind face restoration [35] [6], facial landmarks [4], parsing maps [54], and component heatmaps [60] are typically utilized as external guidance labels.…”

Plug-and-play approach to class-adapted blind image deblurring

“…Niknejad et al introduce a new image denoising method, tailored to specific classes of images, for Gaussian and Poisson noise, based on an importance sampling approach [33,34]. Similarly, in [8], Anwar et al use an external database of images that belong to the specific class to extract the set of "support patches" used in the restoration process. Remez et al approach class-aware image denoising by using deep neural networks [39]; they first perform image classification to classify images into classes, followed by denoising.…”

Hyperspectral Image Denoising With Dual Deep CNN

“…In the field of computer vision, clear images from external databases are used to assist denoising of target images [17]- [20]. For example, in [21] Anwar et al propose matching similar image patches for each region from the database of the same category images, and then the method completes the denoising in the transform domain. Based on the early conventional algorithm [19], [22], Xu et al [23] proposed to exploit useful information in external and internal data.…”