A 16-core processor with both message-passing and shared-memory inter-core communication mechanisms is implemented in 65 nm CMOS. Message-passing communication is enabled in a 3 × 6 Mesh packet-switched network-on-chip, and shared-memory communication is supported using the shared memory within each cluster. The processor occupies 9.1 mm ² and operates fully functional at a clock rate of 750 MHz at 1.2 V and maximum 800 MHz at 1.3 V. Each core dissipates 34 mW under typical conditions at 750 MHz and 1.2 V while executing embedded applications such as an LDPC decoder, a 3780-point FFT module, an H.264 decoder and an LTE channel estimator.

In recent years, the rapid prevalence of high-definition video in Internet of Things (IoT) systems has been directly facilitated by advances in imaging sensor technology. To adapt to limited uplink bandwidth, most media platforms opt to compress videos to bitrate streams for transmission. However, this compression often leads to significant texture loss and artifacts, which severely degrade the Quality of Experience (QoE). We propose a latent feature diffusion model (LFDM) for compressed video quality enhancement, which comprises a compact edge latent feature prior network (ELPN) and a conditional noise prediction network (CNPN). Specifically, we first pre-train ELPNet to construct a latent feature space that captures rich detail information for representing sharpness latent variables. Second, we incorporate these latent variables into the prediction network to iteratively guide the generation direction, thus resolving the problem that the direct application of diffusion models to temporal prediction disrupts inter-frame dependencies, thereby completing the modeling of temporal correlations. Lastly, we innovatively develop a Grouped Domain Fusion module that effectively addresses the challenges of diffusion distortion caused by naive cross-domain information fusion. Comparative experiments on the MFQEv2 benchmark validate our algorithm’s superior performance in terms of both objective and subjective metrics. By integrating with codecs and image sensors, our method can provide higher video quality.

Surprising performance has been achieved in style transfer since deep learning was introduced to it. However, the existing state-of-the art (SOTA) algorithms either suffer from quality issues or high computational complexity. The quality issues include shape retention and the adequacy of style migration, and the computational complexity is reflected in the network complexity and additional updates when the style changes. To deal with the above problems, we propose a novel low computational complexity arbitrary style transfer algorithm (LCCStyle) that mainly consists of a transformation feature module (TFM) and learning transformation module (LTM). The TFM is responsible for transforming the content feature map into the stylized feature map without impact on the integrity of content information, which contributes to good shape retention and full style migration. In addition, to avoid additional updates when the style changes, we propose a new training mechanism for arbitrary style transfer to directly generate the parameters of the TFM by a hyper-network. However, the widely used hyper-networks are composed of fully connected layers, which cause a large number of parameters. Hence, we designed a hyper-network (LTM) consisting of one-dimensional convolution to adapt to the characteristics of the Gram matrix of the style feature map, contributing to a small model size and having no impact on quality. Quantitative comparison and user study show that LCCStyle achieves high performance both on the adequacy of style migration and shape retention. Furthermore, compared with the SOTAs, the size of the proposed model is reduced by a large margin of nearly 51.4%99.6%. When the input is 512512 pixels, the processing speeds in the cases of unchanged style and constantly changing style are increased by at least 135% and 227%, respectively. On an Nvidia TITAN RTX GPU, LCCStyle reaches 60fps for 720p video and takes only 1s to process 8K images.

Recently, Deep Convolutional Neural Networks (DCNNs) have achieved remarkable progress in computer vision community, including in style transfer tasks. Normally, most methods feed the full image to the DCNN. Although highquality results can be achieved in this manner, several underlying problems arise. For one, with the increase in image resolution, the memory footprint will increase dramatically, leading to high latency and massive power consumption. Furthermore, these methods are usually unable to integrate with the commercial image signal processor (ISP), which processes the image in a line-sequential manner. To solve the above problems, we propose a novel ISP-friendly deep learning-based style transfer algorithm: SequentialStyle. A brand new line-sequential processing mode is proposed, where the image is torn into strips, and each strip is sequentially processed, contributing to less memory demand. We further propose a Spatial-Temporal Synergistic (STS) mechanism that decouples the previously simplex 2-D image style transfer into spatial feature processing (in-strip) and temporal correlation transmission (in-between strips). Compared with the SOTA style transfer algorithms, experimental results show that our SequentialStyle is competitive. Besides, SequentialStyle has less demand for memory consumption, even for the images whose resolutions are 4k or higher.