So Yeon Jo’s research while affiliated with LG Uplus and other places

Deep convolutional neural networks (CNNs) have recently made significant advances in the inverse tone mapping technique, which generates a high dynamic range (HDR) image from a single low dynamic range (LDR) image that has lost information in over- and under-exposed regions. The end-to-end inverse tone mapping approach specifies the dynamic range in advance, thereby limiting dynamic range expansion. In contrast, the method of generating multiple exposure LDR images from a single LDR image and subsequently merging them into an HDR image enables flexible dynamic range expansion. However, existing methods for generating multiple exposure LDR images require an additional network for each exposure value to be changed or a process of recursively inferring images that have different exposure values. Therefore, the number of parameters increases significantly due to the use of additional networks, and an error accumulation problem arises due to recursive inference. To solve this problem, we propose a novel network architecture that can control arbitrary exposure values without adding networks or applying recursive inference. The training method of the auxiliary classifier-generative adversarial network structure is employed to generate the image conditioned on the specified exposure. The proposed network uses a newly designed spatially-adaptive normalization to address the limitation of existing methods that cannot sufficiently restore image detail due to the spatially equivariant nature of the convolution. Spatially-adaptive normalization facilitates restoration of the high frequency component by applying different normalization parameters to each element in the feature map according to the characteristics of the input image. Experimental results show that the proposed method outperforms state-of-the-art methods, yielding a 5.48dB higher average peak signal-to-noise ratio, a 0.05 higher average structure similarity index, a 0.28 higher average multi-scale structure similarity index, and a 7.36 higher average HDR-VDP-2 for various datasets.

Rain streaks are one of the main factors that degrade the performance of computer vision algorithms. Therefore, a preprocessing method is needed to remove rain streaks from rainy images. The main issue of the rain removal task is to prevent over (or under) de-raining. Over de-raining means that the background details are removed along with rain streaks in light rain, and under de-raining means that the rain streaks are not completely removed in heavy rain. These occur as the density of rain and intensity of rain streaks vary. In order to solve this, this paper proposes a two-step rain removal method. The proposed system first estimates the rain streaks image redefined with a simple operation from an input rainy image. The proposed rain streaks image contains rain density and rain streak intensity for the rainy image. By using this, the proposed system can adaptively remove rain streaks from images captured in various rain conditions. In addition, we propose a novel architectural unit, the elementwise attentive gating block, which is an optimized block used to deal with high frequency rain streaks. The proposed block selectively passes the desired components from the input feature maps by applying different weights to each element. It helps to clearly extract the rain streaks, and as a result, there are no traces of rain streaks on the restored image. The proposed method outperforms previous rain removal algorithms for both synthetic and real-world images.

Inverse tone mapping aims at recovering the lost scene radiances from a single exposure image. With the successful use of deep learning in numerous applications, many inverse tone mapping methods use convolution neural networks in a supervised manner. As these approaches are trained with many pre-fixed high dynamic range (HDR) images, they fail to flexibly expand the dynamic ranges of images. To overcome this limitation, we consider a multiple exposure image synthesis approach for HDR imaging. In particular, we propose a pair of neural networks that represent mappings between images that have exposure levels one unit apart (stop-up/down network). Therefore, it is possible to construct two positive-feedback systems to generate images with greater or lesser exposure. Compared to previous works using the conditional generative adversarial learning framework, the stop-up/down network employs HDR friendly network structures and several techniques to stabilize the training processes. Experiments on HDR datasets demonstrate the advantages of the proposed method compared to conventional methods. Consequently, we apply our approach to restore the full dynamic range of scenes agilely with only two networks and generate photorealistic images in complex lighting situations.

In this paper, we propose an efficient and lightweight deep neural network, LW‐HDRNET, which quickly and accurately reconstructs tone‐mapped high dynamic range (HDR) images. The proposed network generates over‐exposed and under‐exposed images from a single LDR image and then reconstructs the tone‐mapped HDR image. Experimental results show that the performance is better than the existing methods and has up to 4,000 times fewer parameters.

Deep neural networks (DNNs) have been applied to various fields and achieved high performances. However, they require significant computing resources because of their numerous parameters, even though some of those parameters are redundant and do not contribute to the DNN performance. Recently, to address this problem, many knowledge distillation-based methods have been proposed to compress a large DNN model into a small model. In this paper, we propose a novel knowledge distillation method that can compress a vehicle maker classification system based on a cascaded convolutional neural network (CNN) into a single CNN structure. The system uses mask regions with CNN features (Mask R-CNN) as a preprocessor for the vehicle region detection and has a structure to be used in conjunction with a CNN classifier. By the preprocessor, the classifier can receive the background-removed vehicle image, which allows the classifier to have more attention to the vehicle region. With this cascaded structure, the system can classify the vehicle makers at about 91% performance. Most of all, when we compress the system into a single CNN structure through the proposed knowledge distillation method, it demonstrates about 89% accuracy, in which only about 2% of the accuracy is lost. Our experimental results show that the proposed method is superior to the conventional knowledge distillation method in terms of performance transfer.

An increase in the number of electrical vehicles has resulted in an increase in the number of electrical vehicle charging stations. As a result, the electricity load consumed by charging stations has become large enough to de-stabilize the electricity supply system. Therefore, real-time monitoring of how much electricity each charging station is consuming has become very much important. However, only limited information such as charging time is available from the operators of electric vehicle charging stations. The actual electricity consumption data is not provided in real time. Conventional methods estimate the accumulated electricity consumption of charging stations using a linear regression curve. However, an estimate of the electricity consumption for each charge is needed. In this paper, we propose an advanced electricity estimation system which predicts the energy consumption for each charge. The proposed method uses a constraint-aware non-linear regression curve, and performs additional data selection processes. The experimental results show that the proposed system achieves about 73% regression accuracy. In addition, the proposed system can display the energy consumption per hour and visualize this information on a map. This makes it possible to monitor the electricity consumption of the charging stations in real-time and by location, which helps to select appropriate locations where new vehicle charging stations need to be installed.