Seungyong Ko

Single image super-resolution using locally adaptive multiple linear regression.

This paper presents a regularized superresolution (SR) reconstruction method using locally adaptive multiple linear regression to overcome the limitation of spatial resolution of digital images. In order to make the SR problem better-posed, the proposed method incorporates the locally adaptive multiple linear regression into the regularization process as a local prior. The local regularization prior assumes that the target high-resolution (HR) pixel is generated by a linear combination of similar pixels in differently scaled patches and optimum weight parameters. In addition, we adapt a modified version of the nonlocal means filter as a smoothness prior to utilize the patch redundancy. Experimental results show that the proposed algorithm better restores HR images than existing state-of-the-art methods in the sense of the most objective measures in the literature.

Multisensor Super Resolution Using Directionally-Adaptive Regularization for UAV Images

In various unmanned aerial vehicle (UAV) imaging applications, the multisensor super-resolution (SR) technique has become a chronic problem and attracted increasing attention. Multisensor SR algorithms utilize multispectral low-resolution (LR) images to make a higher resolution (HR) image to improve the performance of the UAV imaging system. The primary objective of the paper is to develop a multisensor SR method based on the existing multispectral imaging framework instead of using additional sensors. In order to restore image details without noise amplification or unnatural post-processing artifacts, this paper presents an improved regularized SR algorithm by combining the directionally-adaptive constraints and multiscale non-local means (NLM) filter. As a result, the proposed method can overcome the physical limitation of multispectral sensors by estimating the color HR image from a set of multispectral LR images using intensity-hue-saturation (IHS) image fusion. Experimental results show that the proposed method provides better SR results than existing state-of-the-art SR methods in the sense of objective measures.

Low-light image enhancement using variational optimization-based Retinex model

This paper presents an optimization-based low-light image enhancement method using spatially adaptive �������� -norm based Retinex model. The proposed method adaptively enforces the regularization parameter using the spatially adaptive weight map, which is generated using the bright channel prior (BCP) and local variance map. Since the proposed weight map assigns the smaller weight value at the bright and edge region, the proposed method can perform weak noise reduction to preserve the edges and textures. In addition, the simplified version of the proposed method is presented using the FFT and quantized weight values for the application to consumer devices. Experimental results show that the proposed method can provide better enhanced result without the ι2 -norm minimization artifacts at the low computational cost.

Artifact-Free Low-Light Video Enhancement Using Temporal Similarity and Guide Map

This paper presents a low-light video restoration algorithm using similar patches among temporally adjacent frames. The proposed artifact-free low-light video restoration algorithm consists of three steps: 1) brightness enhancement using similar patches among temporally adjacent frames and adaptive accumulation; 2) improved color assignment to reduce color distortion; and 3) image fusion for saturation reduction using the guide map. The proposed brightness enhancement step guarantees not to produce any undesired artifacts because of searching the most similar patches among given set of temporally adjacent frames. The color assignment and fusion steps enable a fully automatic color preservation and average brightness control. Experimental results show that the proposed algorithm can better restore high-quality videos without undesired artifacts such as noise amplification, flicker, color distortion, and brightness saturation. As a result, the proposed algorithm can be implemented in a wide range of digital imaging applications such as video surveillance systems and advanced driver assistance systems.

Flicker-free low-light video enhancement using patch-similarity and adaptive accumulation

Recently, the various low-light enhancement methods have been proposed for consumer electronic devices. Although the existing methods provide the better brightness enhancement results, these methods generate the flicker effects during the video enhancement process. Flicker effects are caused by ignoring the correlation information between adjacent frames (i.e. inter-frames). To minimize the flicker effects, the proposed method uses the patch-similarity and adaptive accumulation in the inter-frames domain, and it makes the mean brightness values of enhanced video frames be preserved. The experimental results show that the proposed method can better improve the video frames without flicker effects than existing enhancement methods, and it can be applied to the image signal processing (ISP) chain for consumer electronic devices.

Variational framework for low-light image enhancement using optimal transmission map and combined ℓ1 and ℓ2-minimization

Abstract This paper presents a novel variational framework for low-light image enhancement. The proposed enhancement algorithm simultaneously performs brightness enhancement and noise reduction using a variational optimization. An edge-preserved noise reduction is performed by minimizing the total variation constraint term in the energy function. In addition, the proposed method estimates the optimal transmission map to restore the low-light image by minimizing the l 2 -norm smoothness and data-fidelity terms. To minimize the proposed energy functional, the proposed method splits the l 1 -derivative term under the split Bregman iteration framework. The performance of the proposed method is evaluated using both simulated and natural low-light images. Experimental results show that the proposed enhancement method can significantly improve the quality of the low-light images without noise amplification.

Local self similarity-based super-resolution for asymmetric dual-camera

This paper presents a super-resolution (SR) method for the asymmetric dual-camera system. The proposed method restores the high-resolution (HR) image using the local self-similarity between two input images as wide- and tele-view images. The proposed method consists of three steps: registration and warping processes to reduce the disparity between the input images, high-frequency patch extraction from the tele-view image, and super-resolution reconstruction using local self-similarity property. Experimental results show that the proposed method can significantly restore the HR image than existing interpolation and SR methods.

Low-light image enhancement using fast adaptive binning for mobile phone cameras

The existing low-light enhancement methods provide better enhancement results, and it cannot be implemented on the real-time processing due to the computational load. Also, these methods generate the unnatural artifacts such as noise amplification, color distortion and saturation problem. To solve this problem, this paper presents a fast adaptive binning method using local amplification ratio map and improved cumulative density function (CDF). The experimental results show that the proposed method provides significantly enhanced results than existing methods, and it can be adapted to consumer devices by finite impulse response (FIR) structure.