Showing papers by "Huizhu Jia published in 2017"

LLCNN: A convolutional neural network for low-light image enhancement

Abstract: In this paper, we propose a CNN based method to perform low-light image enhancement. We design a special module to utilize multiscale feature maps, which can avoid gradient vanishing problem as well. In order to preserve image textures as much as possible, we use SSIM loss to train our model. The contrast of low-light images can be adaptively enhanced using our method. Results demonstrate that our CNN based method outperforms other contrast enhancement methods.

Low-light image enhancement using CNN and bright channel prior

Abstract: In this paper, we propose a joint framework to enhance images under low-light conditions. First, a convolutional neural network (CNN) based architecture is proposed to denoise low-light images. Then, based on atmosphere scattering model, we introduce a low-light model to enhance image contrast. In our low-light model, we propose a simple but effective image prior, bright channel prior, to estimate the transmission parameter; besides, an effective filter is designed to adaptively estimate environment light in different image areas. Experimental results demonstrate that our method achieves superior performance over other methods.

Fast Rate Distortion Optimized Quantization Method Based on Early Detection of Zero Block for HEVC

Abstract: This paper presents an efficient zero block early detection method to accelerate Rate Distortion Optimized Quantization (RDOQ) for High Efficiency Video Coding (HEVC). RDOQ brings significant improvement of coding performance, but it results in high computational complexity to determine the best quantization levels with rate and distortion optimization operations. It is worthwhile to detect all-zero-quantized blocks before RDOQ since a lot of transform units are zero blocks after RDOQ process. In this paper, we analyze the transform coefficients characteristics in zero blocks firstly. And then, the relationship among the zero block detection thresholds, transform unit sizes and quantization parameters is studied. An adaptive zero block detection model is designed to speed up RDOQ process. Experimental results show that the proposed method achieves 44.10% and 41.68% quantization time saving with only average 0.16% and 0.01% BD-Rate loss under random access and low delay configuration, respectively.

Blind restoration for nonuniform aerial images using nonlocal Retinex model and shearlet-based higher-order regularization

Abstract: Aerial images are often degraded by space-varying motion blurs and simultaneous uneven illumination. To recover a high-quality aerial image from its nonuniform version, we propose a patchwise restoration approach based on a key observation that the degree of blurring is inevitably affected by the illumination conditions. A nonlocal Retinex model is developed to accurately estimate the reflectance component from the degraded aerial image. Thereafter, the uneven illumination is corrected well. Then nonuniform coupled blurring in the enhanced reflectance image is alleviated and transformed toward uniform distribution, which will facilitate the subsequent deblurring. For constructing the multiscale sparsified regularization, the discrete shearlet transform is improved to better represent anisotropic image features in terms of directional sensitivity and selectivity. In addition, a new adaptive variant of total generalized variation is proposed to act as the structure-preserving regularizer. These complementary regularizers are elegantly integrated into an objective function. The final deblurred image with uniform illumination can be obtained by applying a fast alternating direction scheme to solve the derived function. The experimental results demonstrate that our algorithm can not only effectively remove both the space-varying illumination and motion blurs in aerial images, but also recover the abundant details of aerial scenes with top-level objective and subjective quality, and outperforms other state-of-the-art restoration methods.

An improved adaptive quantization method based on perceptual CU early splitting for HEVC

Abstract: High Efficiency Video Coding is the latest video coding standard, and it can achieve significant compression performance with numerous coding tools. It supports different quantization parameters for each different coding unit in any depth coding unit. However, the adaptive quantization (AQ) method in current HEVC suffers from the underestimated spatial activity and Lagrange multiplier selection problems. What's more, no perceptual considering are taken into the AQ model, thus it cannot obtain performance correctly and reasonably. Therefore, in this paper, we first solve the problems existed in current AQ method and then we propose a novel perceptual AQ method (PAQ) based on an adaptive perceptual CU early splitting algorithm to improve performance. Experiments demonstrate that with SSIM (Structure Similarity) as metric, it can achieve more than −9.3% BD-Rate saving with proposed method compared with the HM10.0 encoder, which outperforms than the existed methods.

Adaptive feature selection based on local descriptor distinctive degree for vehicle retrieval application

Abstract: Performing image retrieval in large image database is becoming popular with the development of multimedia technology. Recently, ISO/IEC moving pictures experts group (MPEG) drafts compact descriptors for visual search (CDVS) to support the related applications. The state-of-the-art feature selection strategy in CDVS adopts a priori relevance measure to guide the selection. However, this method ignores the gradient information of the described feature. In this paper, we adopt CDVS to address traffic vehicle search in large database. After detailedly analyzing to the local descriptor, we firstly define local descriptor distinctive degree based on the gradient quantity and the spatial gradient distribution energy of the feature. Then we propose our adaptive feature selection method by combing feature distinctive degree and the priori information. The proposed method is proven to be better than the standard algorithm in CDVS and it almost introduces 10% mean average precision (MAP) and top match rate increase in low bit rate mode.

Learning a collaborative multiscale dictionary based on robust empirical mode decomposition

Abstract: Dictionary learning is a challenge topic in many image processing areas. The basic goal is to learn a sparse representation from an overcomplete basis set. Due to combining the advantages of generic multiscale representations with learning based adaptivity, multiscale dictionary representation approaches have the power in capturing structural characteristics of natural images. However, existing multiscale learning approaches still suffer from three main weaknesses: inadaptability to diverse scales of image data, sensitivity to noise and outliers, difficulty to determine optimal dictionary structure. In this paper, we present a novel multiscale dictionary learning paradigm for sparse image representations based on an improved empirical mode decomposition. This powerful data-driven analysis tool for multi-dimensional signal can fully adaptively decompose the image into multiscale oscillating components according to intrinsic modes of data self. This treatment can obtain a robust and effective sparse representation, and meanwhile generates a raw base dictionary at multiple geometric scales and spatial frequency bands. This dictionary is refined by selecting optimal oscillating atoms based on frequency clustering. In order to further enhance sparsity and generalization, a tolerance dictionary is learned using a coherence regularized model. A fast proximal scheme is developed to optimize this model. The multiscale dictionary is considered as the product of oscillating dictionary and tolerance dictionary. Experimental results demonstrate that the proposed learning approach has the superior performance in sparse image representations as compared with several competing methods. We also show the promising results in image denoising application.

Fast rate distortion optimized quantization method for HEVC

Abstract: Rate-Distortion Optimized Quantization (RDOQ) brings significant improvement of coding performance in High Efficiency Video Coding (HEVC). However, it results in high computational complexity to determine the best quantization levels for each transform coefficient when applying rate and distortion optimization operation. In this paper, we firstly proposed an efficient way to skip the all zero coding units. Then we further propose a fast RDOQ scheme by skipping the optimization step of All Quantized Zero Blocks except DC Coefficient (AQZB-DC). Moreover, a rate difference model is established to select optimal quantization level for AQZB-DC blocks. Experiments are carried out on reference software HM 16.0 and the results show that the proposed method achieves 42.00% and 39.63% quantization time saving under Random Access (RA) and Low Delay (LD) configuration on average, while the BD-Rate loss is only 0.03% and 0.06%, respectively.

A cache-based bandwidth optimized motion compensation architecture for video decoder

Abstract: In video decoder applications, motion compensation (MC) is bandwidth consuming because of the non-regular memory access. Especially with the popularity of UHD video and the development of new coding standard (HEVC), external memory bandwidth becomes a crucial bottleneck. In this paper, we propose an area efficiency cache-based bandwidth optimization strategy to minimize the memory bandwidth. First a four-way parallel cache architecture is described. Then partially replacement strategy is proposed to further reduce memory bandwidth and power consumption. At last a column based storage scheme is provided to reduce the precharge/active frequency. We realize this idea using high level synthesis, which allow multiple iterations with quick turnaround time for micro architecture changes, and the results show that the averagely bandwidth reduction is up to 79.9% with moderate resource utilization, which outperforms the state-of-the-art works.

Sparsity-Promoting Adaptive Coding with Robust Empirical Mode Decomposition for Image Restoration

Abstract: In this paper, a novel data-driven sparse coding framework is proposed to solve image restoration problem based on a robust empirical mode decomposition. This powerful analysis tool for multi-dimensional signals can adaptively decompose images into multiscale oscillating components according to intrinsic modes of data self. This treatment can obtain very effective sparse representation, and meanwhile generates a dictionary at multiple geometric scales and frequency bands. The distribution of sparse coefficients is reliably approximated by generalized Gaussian model. Moreover, a sparse approximation of blur kernel is also obtained as a strong prior. Finally, latent image and blur kernel can be jointly estimated via alternating optimization scheme. The extensive experiments show that our approach can effectively and efficiently recover the sharpness of local structures and suppress undesirable artifacts.

Content Adaptive Constraint Based Image Upsampling

Abstract: In this paper, we present a novel image upsampling method within a two-stage framework to reconstruct different image content (large-scale edges and small-scale structures). First, we utilize a total variation (TV) filter for image decomposition which decomposes an image content into structure component and texture component. In the first stage, the structure component is enhanced by a shock filter and an improved non-local means filter, then combines with the texture component to generate initial high-resolution (HR) image. In the second stage, the gradient of initial HR image is regarded as an edge preserving constraint to reconstruct the texture component. Experimental results demonstrate that the new approach can reconstruct faithfully the HR images with sharp edges and texture structures, and annoying artifacts (blurring, jaggies, ringing, etc.) are greatly suppressed. It outperforms the state-of-the-art approaches, based on subjective and objective evaluations.

Computational Calibration and Correction for Gigapixel Imaging System

Abstract: Large field of view (FOV) imaging with high spatial resolution has been increasingly required for numerous applications in recent years. Obviously, conventional photosensitive detector with tens of megapixels cannot satisfy the requirement. As a result, gigapixel cameras based on the multi-aperture imaging have become a possible solution to overcome the above limitation. In this paper, we developed an alternative gigapixel imaging system which implements the multiple CMOS chips mosaic in the external optical path and presented the computation methods for calibrating the vignetting distributions and other geometric parameters in the system. Consequently, our gigapixel imaging system has achieved the performance of 24 Hz, 0.2Giga, single-pixel resolution.