Priyam Chatterjee

Bio: Priyam Chatterjee is an academic researcher from University of California, Santa Cruz. The author has contributed to research in topics: Image processing & Non-local means. The author has an hindex of 16, co-authored 31 publications receiving 2017 citations. Previous affiliations of Priyam Chatterjee include Facebook & Indian Institute of Technology Bombay.

Is Denoising Dead

Abstract: Image denoising has been a well studied problem in the field of image processing. Yet researchers continue to focus attention on it to better the current state-of-the-art. Recently proposed methods take different approaches to the problem and yet their denoising performances are comparable. A pertinent question then to ask is whether there is a theoretical limit to denoising performance and, more importantly, are we there yet? As camera manufacturers continue to pack increasing numbers of pixels per unit area, an increase in noise sensitivity manifests itself in the form of a noisier image. We study the performance bounds for the image denoising problem. Our work in this paper estimates a lower bound on the mean squared error of the denoised result and compares the performance of current state-of-the-art denoising methods with this bound. We show that despite the phenomenal recent progress in the quality of denoising algorithms, some room for improvement still remains for a wide class of general images, and at certain signal-to-noise levels. Therefore, image denoising is not dead - yet.

Patch-Based Near-Optimal Image Denoising

Abstract: In this paper, we propose a denoising method motivated by our previous analysis of the performance bounds for image denoising. Insights from that study are used here to derive a high-performance practical denoising algorithm. We propose a patch-based Wiener filter that exploits patch redundancy for image denoising. Our framework uses both geometrically and photometrically similar patches to estimate the different filter parameters. We describe how these parameters can be accurately estimated directly from the input noisy image. Our denoising approach, designed for near-optimal performance (in the mean-squared error sense), has a sound statistical foundation that is analyzed in detail. The performance of our approach is experimentally verified on a variety of images and noise levels. The results presented here demonstrate that our proposed method is on par or exceeding the current state of the art, both visually and quantitatively.

Clustering-Based Denoising With Locally Learned Dictionaries

Abstract: In this paper, we propose K-LLD: a patch-based, locally adaptive denoising method based on clustering the given noisy image into regions of similar geometric structure. In order to effectively perform such clustering, we employ as features the local weight functions derived from our earlier work on steering kernel regression . These weights are exceedingly informative and robust in conveying reliable local structural information about the image even in the presence of significant amounts of noise. Next, we model each region (or cluster)-which may not be spatially contiguous-by ldquolearningrdquo a best basis describing the patches within that cluster using principal components analysis. This learned basis (or ldquodictionaryrdquo) is then employed to optimally estimate the underlying pixel values using a kernel regression framework. An iterated version of the proposed algorithm is also presented which leads to further performance enhancements. We also introduce a novel mechanism for optimally choosing the local patch size for each cluster using Stein's unbiased risk estimator (SURE). We illustrate the overall algorithm's capabilities with several examples. These indicate that the proposed method appears to be competitive with some of the most recently published state of the art denoising methods.

PiCam: an ultra-thin high performance monolithic camera array

Abstract: We present PiCam (Pelican Imaging Camera-Array), an ultra-thin high performance monolithic camera array, that captures light fields and synthesizes high resolution images along with a range image (scene depth) through integrated parallax detection and superresolution. The camera is passive, supporting both stills and video, low light capable, and small enough to be included in the next generation of mobile devices including smartphones. Prior works [Rander et al. 1997; Yang et al. 2002; Zhang and Chen 2004; Tanida et al. 2001; Tanida et al. 2003; Duparre et al. 2004] in camera arrays have explored multiple facets of light field capture - from viewpoint synthesis, synthetic refocus, computing range images, high speed video, and micro-optical aspects of system miniaturization. However, none of these have addressed the modifications needed to achieve the strict form factor and image quality required to make array cameras practical for mobile devices. In our approach, we customize many aspects of the camera array including lenses, pixels, sensors, and software algorithms to achieve imaging performance and form factor comparable to existing mobile phone cameras.Our contributions to the post-processing of images from camera arrays include a cost function for parallax detection that integrates across multiple color channels, and a regularized image restoration (superresolution) process that takes into account all the system degradations and adapts to a range of practical imaging conditions. The registration uncertainty from the parallax detection process is integrated into a Maximum-a-Posteriori formulation that synthesizes an estimate of the high resolution image and scene depth. We conclude with some examples of our array capabilities such as postcapture (still) refocus, video refocus, view synthesis to demonstrate motion parallax, 3D range images, and briefly address future work.

Systems and Methods for Synthesizing Images from Image Data Captured by an Array Camera Using Restricted Depth of Field Depth Maps in which Depth Estimation Precision Varies

Abstract: Systems and methods are described for generating restricted depth of field depth maps. In one embodiment, an image processing pipeline application configures a processor to: determine a desired focal plane distance and a range of distances corresponding to a restricted depth of field for an image rendered from a reference viewpoint; generate a restricted depth of field depth map from the reference viewpoint using the set of images captured from different viewpoints, where depth estimation precision is higher for pixels with depth estimates within the range of distances corresponding to the restricted depth of field and lower for pixels with depth estimates outside of the range of distances corresponding to the restricted depth of field; and render a restricted depth of field image from the reference viewpoint using the set of images captured from different viewpoints and the restricted depth of field depth map.

FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising

Abstract: Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for denoising images with different noise levels. They also lack flexibility to deal with spatially variant noise, limiting their applications in practical denoising. To address these issues, we present a fast and flexible denoising convolutional neural network, namely FFDNet, with a tunable noise level map as the input. The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance. In contrast to the existing discriminative denoisers, FFDNet enjoys several desirable properties, including: 1) the ability to handle a wide range of noise levels (i.e., [0, 75]) effectively with a single network; 2) the ability to remove spatially variant noise by specifying a non-uniform noise level map; and 3) faster speed than benchmark BM3D even on CPU without sacrificing denoising performance. Extensive experiments on synthetic and real noisy images are conducted to evaluate FFDNet in comparison with state-of-the-art denoisers. The results show that FFDNet is effective and efficient, making it highly attractive for practical denoising applications.

Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections

Abstract: In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and deconvolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers act as the feature extractor, which capture the abstraction of image contents while eliminating noises/corruptions. Deconvolutional layers are then used to recover the image details. We propose to symmetrically link convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum. First, the skip connections allow the signal to be back-propagated to bottom layers directly, and thus tackles the problem of gradient vanishing, making training deep networks easier and achieving restoration performance gains consequently. Second, these skip connections pass image details from convolutional layers to deconvolutional layers, which is beneficial in recovering the original image. Significantly, with the large capacity, we can handle different levels of noises using a single model. Experimental results show that our network achieves better performance than recent state-of-the-art methods.

Plug-and-Play priors for model based reconstruction

Abstract: Model-based reconstruction is a powerful framework for solving a variety of inverse problems in imaging. In recent years, enormous progress has been made in the problem of denoising, a special case of an inverse problem where the forward model is an identity operator. Similarly, great progress has been made in improving model-based inversion when the forward model corresponds to complex physical measurements in applications such as X-ray CT, electron-microscopy, MRI, and ultrasound, to name just a few. However, combining state-of-the-art denoising algorithms (i.e., prior models) with state-of-the-art inversion methods (i.e., forward models) has been a challenge for many reasons. In this paper, we propose a flexible framework that allows state-of-the-art forward models of imaging systems to be matched with state-of-the-art priors or denoising models. This framework, which we term as Plug-and-Play priors, has the advantage that it dramatically simplifies software integration, and moreover, it allows state-of-the-art denoising methods that have no known formulation as an optimization problem to be used. We demonstrate with some simple examples how Plug-and-Play priors can be used to mix and match a wide variety of existing denoising models with a tomographic forward model, thus greatly expanding the range of possible problem solutions.

Toward Convolutional Blind Denoising of Real Photographs

Abstract: While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. The main reason is that their learned models are easy to overfit on the simplified AWGN model which deviates severely from the complicated real-world noise model. In order to improve the generalization ability of deep CNN denoisers, we suggest training a convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs. On the one hand, both signal-dependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBDNet. To further provide an interactive strategy to rectify denoising result conveniently, a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Extensive experimental results on three datasets of real-world noisy pho- tographs clearly demonstrate the superior performance of CBDNet over state-of-the-arts in terms of quantitative met- rics and visual quality. The code has been made available at https://github.com/GuoShi28/CBDNet.