Related papers: BiMaCoSR: Binary One-Step Diffusion Model Leveragi…
Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…
Recent advancements in diffusion models have demonstrated remarkable success in various image generation tasks. Building upon these achievements, diffusion models have also been effectively adapted to image restoration tasks, e.g.,…
Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy…
Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…
Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high…
Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing…
Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment. Quantization emerges as one of the most effective…
Sampling from diffusion models involves a slow iterative process that hinders their practical deployment, especially for interactive applications. To accelerate generation speed, recent approaches distill a multi-step diffusion model into a…
Single-Image-Super-Resolution (SISR) is a classical computer vision problem that has benefited from the recent advancements in deep learning methods, especially the advancements of convolutional neural networks (CNN). Although…
This paper proposes an image-based robot motion planning method using a one-step diffusion model. While the diffusion model allows for high-quality motion generation, its computational cost is too expensive to control a robot in real time.…
Blind face restoration (BFR) is important while challenging. Prior works prefer to exploit GAN-based frameworks to tackle this task due to the balance of quality and efficiency. However, these methods suffer from poor stability and…
Recent advancements in diffusion models have positioned them at the forefront of image generation. Despite their superior performance, diffusion models are not without drawbacks; they are characterized by complex architectures and…
Recently, open-source video diffusion models (VDMs), such as WanX, Magic141 and HunyuanVideo, have been scaled to over 10 billion parameters. These large-scale VDMs have demonstrated significant improvements over smaller-scale VDMs across…
Diffusion models (DMs), lauded for their generative performance, are computationally prohibitive due to their billion-scale parameters and iterative denoising dynamics. Existing efficiency techniques, such as quantization, timestep…
Real-world image super-resolution (Real-ISR) aims to reconstruct high-resolution images from low-resolution inputs degraded by complex, unknown processes. While many Stable Diffusion (SD)-based Real-ISR methods have achieved remarkable…
While generative diffusion models excel in producing high-quality images, they can also be misused to mimic authorized images, posing a significant threat to AI systems. Efforts have been made to add calibrated perturbations to protect…
A low-resolution digital surface model (DSM) features distinctive attributes impacted by noise, sensor limitations and data acquisition conditions, which failed to be replicated using simple interpolation methods like bicubic. This causes…
Sparse matrices and tensors are ubiquitous throughout multiple subfields of computing. The widespread usage of sparse data has inspired many in-memory and on-disk storage formats, but the only widely adopted storage specifications are the…
Deploying massive number of antennas at the base station side can boost the cellular system performance dramatically. Meanwhile, it however involves significant additional radio-frequency (RF) front-end complexity, hardware cost and power…
Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content, opening up the opportunity to improve image super-resolution (SR) tasks. Recent solutions for these tasks often…