Related papers: Considerations and Results in Multimedia and DVB A…
Visible images have been widely used for motion estimation. Thermal images, in contrast, are more challenging to be used in motion estimation since they typically have lower resolution, less texture, and more noise. In this paper, a novel…
Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this…
This article considers the issue of the development, production, and application of nanocomposite materials in telecommunication networks for the optical and subterahertz wave ranges. The results are obtained on the base of growing the…
We propose an optimal MMSE precoding technique using quantized signals with constant envelope. Unlike the existing MMSE design that relies on 1-bit resolution, the proposed approach employs uniform phase quantization and the bounding step…
While fully-digital precoding achieves superior performance in massive MIMO systems, it comes with significant drawbacks in terms of computational complexity and power consumption, particularly when operating at millimeter-wave (mmWave)…
Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…
While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to…
Diffusion models have revolutionized text-driven video editing. However, applying these methods to real-world editing encounters two significant challenges: (1) the rapid increase in GPU memory demand as the number of frames grows, and (2)…
This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there are currently no…
Diffusion models have demonstrated superior performance across various generative tasks including images, videos, and audio. However, they encounter difficulties in directly generating high-resolution samples. Previously proposed solutions…
Contrastive Language-Image Pre-training (CLIP) has attracted a surge of attention for its superior zero-shot performance and excellent transferability to downstream tasks. However, training such large-scale models usually requires…
This paper introduces a novel dataset for video enhancement and studies the state-of-the-art methods of the NTIRE 2021 challenge on quality enhancement of compressed video. The challenge is the first NTIRE challenge in this direction, with…
GPUs have been widely used to accelerate computations exhibiting simple patterns of parallelism - such as flat or two-level parallelism - and a degree of parallelism that can be statically determined based on the size of the input dataset.…
Achieving maximum possible rate of inferencing with minimum hardware resources plays a major role in reducing enterprise operational costs. In this paper we explore use of PCIe streaming on FPGA based platforms to achieve high throughput.…
Fourier and related transforms is a family of algorithms widely employed in diverse areas of computational science, notoriously difficult to scale on high-performance parallel computers with large number of processing elements (cores). This…
Monocular Depth Estimation (MDE) is a fundamental 3D vision problem with numerous applications such as 3D scene reconstruction, autonomous navigation, and AI content creation. However, robust and generalizable MDE remains challenging due to…
Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years. Although owning diverse and high-quality generation capabilities, translating these abilities to fine-grained image editing…
Digital cameras are commonly used for diagnostic purposes in large-scale physics experiments. A typical image diagnostic system consists of an optical setup, digital camera, frame grabber, image processing CPU, and data analysis tool. The…
We advocate a domain specific software development methodology for heterogeneous computing platforms such as Multicore CPUs, GPUs and FPGAs. We argue that three specific benefits are realised from adopting such an approach: portable,…
Web developers use base64 formats to include images, fonts, sounds and other resources directly inside HTML, JavaScript, JSON and XML files. We estimate that billions of base64 messages are decoded every day. We are motivated to improve the…