Search

In this paper, we propose a novel image coding framework with semantic-aware visual decomposition towards extremely low bitrate compression. In particular, an input image is analyzed into a semantic map as structural representation and semantic-wise texture representation and further compressed into bitstreams at the encoder side. On the decoder side, the received bitstreams of dual-layer representations are decoded and reconstructed for target image synthesis with generative models. Moreover, the attention mechanism is introduced into the model architecture for texture representation modeling and a coherency regularization is proposed to further optimize the texture representation space by aligning the representation space with the source pixel space for higher synthesis quality. Besides, we also propose a cross-channel entropy module and control the quantization scale to facilitate rate-distortion optimization. Upon compressing the decomposed components into the bitstream, the simple yet effective representation philosophy benefits image compression in many aspects. First, in terms of compression performance, compact representations, and high visual synthesis quality can bring remarkable advantages. Second, the proposed framework yields a physically explainable bitstream composed of the structural segment and semantic-wise texture segments. Third and most importantly, subsequent vision tasks (e.g., content manipulation) can receive fundamental support from the semantic-aware visual decomposition and synthesis mechanism. Extensive experimental results demonstrate the superiority of the proposed framework towards efficient visual representation learning, high efficiency image compression ( < 0.1 bpp), and intelligent visual applications (e.g., manipulation and analysis). [ABSTRACT FROM AUTHOR]

Recent image-to-image (I2I) translation algorithms focus on learning the mapping from a source to a target domain. However, the continuous translation problem that synthesizes intermediate results between two domains has not been well-studied in the literature. Generating a smooth sequence of intermediate results bridges the gap of two different domains, facilitating the morphing effect across domains. Existing I2I approaches are limited to either intra-domain or deterministic inter-domain continuous translation. In this work, we present an effectively signed attribute vector, which enables continuous translation on diverse mapping paths across various domains. In particular, we introduce a unified attribute space shared by all domains that utilize the sign operation to encode the domain information, thereby allowing the interpolation on attribute vectors of different domains. To enhance the visual quality of continuous translation results, we generate a trajectory between two sign-symmetrical attribute vectors and leverage the domain information of the interpolated results along the trajectory for adversarial training. We evaluate the proposed method on a wide range of I2I translation tasks. Both qualitative and quantitative results demonstrate that the proposed framework generates more high-quality continuous translation results against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Machine visual intelligence has exploded in recent years. Large-scale, high-quality image and video datasets significantly empower learning-based machine vision models, especially deep-learning models. However, images and videos are usually compressed before being analyzed in practical situations where transmission or storage is limited, leading to a noticeable performance loss of vision models. In this work, we broadly investigate the impact on the performance of machine vision from image and video coding. Based on the investigation, we propose Just Recognizable Distortion (JRD) to present the maximum distortion caused by data compression that will reduce the machine vision model performance to an unacceptable level. A large-scale JRD-annotated dataset containing over 340,000 images is built for various machine vision tasks, where the factors for different JRDs are studied. Furthermore, an ensemble-learning-based framework is established to predict the JRDs for diverse vision tasks under few- and non-reference conditions, which consists of multiple binary classifiers to improve the prediction accuracy. Experiments prove the effectiveness of the proposed JRD-guided image and video coding to significantly improve compression and machine vision performance. Applying predicted JRD is able to achieve remarkably better machine vision task accuracy and save a large number of bits. [ABSTRACT FROM AUTHOR]

Ever since the founding of the Audio and Video Coding Standard (AVS) Workgroup of China in 2002, it has been dedicated to advancing and innovating the digital audio-video industry with highly efficient and economical encoding/decoding technologies. Three representative generations of video coding standards have been finalized and published, consistently improving the coding performance in the past two decades. The series of AVS standards establish solid foundations for ubiquitous video applications in the areas including acquisition, coding, production, delivery, integrated system, public service, general screen content, and mixed reality media. Along with the standardization process, an extensive amount of studies have been carried out on efficiency-aware designation, algorithm optimization, and hardware implementation of these innovative video coding techniques. This paper explains how those developed techniques provide a lasting impact on the video coding community, extensively, technologically, and systematically. In particular, we provide a comprehensive survey of the three generations of the standards, and timely and in-depth summarize the efforts of the AVS video coding standards in the twenty years. The rate-distortion performance comparisons, in particular in terms of the 8K ultra-high-definition (UHD) contents, reflect the elegant design of the state-of-the-art AVS3 standards. We have also elaborated on a variety of well-established and promising applications, including commercial level real-time 8K encoder, high-frame-rate decoder chip for cell phone, and live streaming solution for sports. In addition, the China Central Television (CCTV) of China Media Group (CMG), the state television of China, has officially launched the first 8K broadcasting channel (CCTV-8K) since 2021 using AVS3. Given the significant success realized by the AVS standards, it is envisioned that a new era of 8K UHD video is arriving. [ABSTRACT FROM AUTHOR]

ZnO nanowires have been grown on polycrystalline ZnGeO:Mn substrates for the first time using a chemical vapor deposition method. Both Zn and ZnO sources were used to supply Zn vapor in the growth process of ZnO nanowires. The ZnGeO:Mn substrates were prepared using solid-state ceramic synthesis methods, and average grain sizes of ~1 μm were achieved. The nanowires of diameters in the range of 100-200 nm and length of ~30 μm were observed. In addition to nanowires, other morphologies of ZnO nanostructures, such as ZnO tetrapods, were observed when Zn powder was used as the source for the CVD growth. The results reveal that polycrystalline substrates are also promising as novel alternative substrates for growth of ZnO nanostructures. The as-synthesized ZnO nanowire/ZnGeO:Mn composites are being developed for future electroluminescent devices. [ABSTRACT FROM AUTHOR]

Image quality assessment (IQA) has been intensively studied, especially for the full-reference (FR) scenario. However, only the mean-squared error (MSE) is widely employed in compression. Why other IQA metrics work ineffectively? We first sum up three main limitations including the computational time, portability, and working manner. To address these problems, we then in this paper propose a new content-weighted MSE (CW-MSE) method to assess the quality of compressed images. The design principle of our model is to use adaptive Gaussian convolution to estimate the influence of image content in a block-based manner, thereby to approximate the human visual perception to image quality. Results of experiments on six popular subjective image quality databases (including LIVE, TID2008, CSIQ, IVC, Toyama and TID2013) confirm the superiority of our CW-MSE over state-of-the-art FR IQA approaches. [ABSTRACT FROM AUTHOR]

In this paper, an optimal entropy-constrained non-uniform scalar quantizer is proposed for the pixel domain DVC. The uniform quantizer is efficient for the hybrid video coding since the residual signals conforming to a single-variance Laplacian distribution. However, the uniform quantizer is not optimal for pixel domain distributed video coding (DVC). This is because the uniform quantizer is not adaptive to the joint distribution of the source and the SI, especially for low level quantization. The signal distribution of pixel domain DVC conforms to the mixture model with multi-variance. The optimal non-uniform quantizer is designed according to the joint distribution, the error between the source and the SI can be decreased. As a result, the bit rate can be saved and the video quality won't sacrifice too much. Accordingly, a better R-D trade-off can be achieved. First, the quantization level is fixed and the optimal RD trade-off is achieved by using a Lagrangian function J( Q). The rate and distortion components is designed based on P( Y| Q). The conditional probability density function of SI Y depend on quantization partitions Q, P( Y| Q), is approximated by a Guassian mixture model at encocder. Since the SI can not be accessed at encoder, an estimation of P( Y| Q) based on the distribution of the source is proposed. Next, J( Q) is optimized by an iterative Lloyd-Max algorithm with a novel quantization partition updating algorithm. To guarantee the convergence of J( Q), the monotonicity of the interval in which the endpoints of the quantizer lie must be satisfied. Then, a quantizer partition updating algorithm which considers the extreme points of the histogram of the source is proposed. Consequently, the entropy-constrained optimal non-uniform quantization partitions are derived and a better RD trade-off is achieved by applying them. Experiment results show that the proposed scheme can improve the performance by 0.5 dB averagely compared to the uniform scalar quantization. [ABSTRACT FROM AUTHOR]

We describe the use of individual zinc oxide (ZnO) micro/nanowires in an electrochemical biosensor for uric acid. The wires were synthesized by chemical vapor deposition and possess uniform morphology and high crystallinity as revealed by scanning electron microscopy, X-ray diffraction, and photoluminescence studies. The enzyme uricase was then immobilized on the surface of the ZnO micro/nanowires by physical adsorption, and this was proven by Raman spectroscopy and fluorescence microscopy. The resulting uric acid biosensor undergoes fast electron transfer between the active site of the enzyme and the surface of the electrode. It displays high sensitivity (89.74 μA cm mM) and a wide linear analytical range (between 0.1 mM and 0.59 mM concentrations of uric acid). This study also demonstrates the potential of the use of individual ZnO micro/nanowires for the construction of highly sensitive nano-sized biosensors. [Figure not available: see fulltext.] [ABSTRACT FROM AUTHOR]