English
Related papers

Related papers: Hybrid SD: Edge-Cloud Collaborative Inference for …

200 papers

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Nikita Starodubcev , Ilya Drobyshevskiy , Denis Kuznedelev , Artem Babenko , Dmitry Baranchuk

Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoising process, hinders real-time deployment in latency-sensitive…

Computer Vision and Pattern Recognition · Computer Science 2025-05-08 Shuaiting Li , Juncan Deng , Zeyu Wang , Kedong Xu , Rongtao Deng , Hong Gu , Haibin Shen , Kejie Huang

Diffusion (score-based) generative models have been widely used for modeling various types of complex data, including images, audios, and point clouds. Recently, the deep connection between forward-backward stochastic differential equations…

Machine Learning · Computer Science 2022-06-22 Weitao Du , Tao Yang , He Zhang , Yuanqi Du

Large language models (LLMs) have shown great potential in natural language processing and content generation. However, current LLMs heavily rely on cloud computing, leading to prolonged latency, high bandwidth cost, and privacy concerns.…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-24 Mingjin Zhang , Jiannong Cao , Xiaoming Shen , Zeyang Cui

As one of the basic tasks of computer vision, object detection has been widely used in many intelligent applications. However, object detection algorithms are usually heavyweight in computation, hindering their implementations on…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Zhiqiang Cao , Zhijun Li , Pan Heng , Yongrui Chen , Daqi Xie , Jie Liu

Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Anwaar Ulhaq , Naveed Akhtar

This paper explores the innovative application of Stable Video Diffusion (SVD), a diffusion model that revolutionizes the creation of dynamic video content from static images. As digital media and design industries accelerate, SVD emerges…

Human-Computer Interaction · Computer Science 2024-05-24 Elijah Miller , Thomas Dupont , Mingming Wang

A potent class of generative models known as Diffusion Probabilistic Models (DPMs) has become prominent. A forward diffusion process adds gradually noise to data, while a model learns to gradually denoise. Sampling from pre-trained DPMs is…

Machine Learning · Computer Science 2023-10-27 Martin Gonzalez , Nelson Fernandez , Thuy Tran , Elies Gherbi , Hatem Hajri , Nader Masmoudi

Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms.…

Computer Vision and Pattern Recognition · Computer Science 2022-12-01 Xingyi Yang , Daquan Zhou , Jiashi Feng , Xinchao Wang

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Yaofo Chen , Shuaicheng Niu , Yaowei Wang , Shoukai Xu , Hengjie Song , Mingkui Tan

Diffusion Model (DM) based Semantic Image Communication (SIC) systems face significant challenges, such as slow inference speed and generation randomness, that limit their reliability and practicality. To overcome these issues, we propose a…

Image and Video Processing · Electrical Eng. & Systems 2025-07-24 Bilal Khalid , Pedro Freire , Sergei K. Turitsyn , Jaroslaw E. Prilepsky

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment.…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Bin Chen , Zhenyu Zhang , Weiqi Li , Chen Zhao , Jiwen Yu , Shijie Zhao , Jie Chen , Jian Zhang

In many industry scale applications, large and resource consuming machine learning models reside in powerful cloud servers. At the same time, large amounts of input data are collected at the edge of cloud. The inference results are also…

Machine Learning · Computer Science 2021-08-31 Amin Banitalebi-Dehkordi , Naveen Vedula , Jian Pei , Fei Xia , Lanjun Wang , Yong Zhang

The task of steel surface defect recognition is an industrial problem with great industry values. The data insufficiency is the major challenge in training a robust defect recognition network. Existing methods have investigated to enlarge…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Yichun Tai , Kun Yang , Tao Peng , Zhenzhen Huang , Zhijiang Zhang

Large language models (LLMs) have transformed natural language processing but face critical deployment challenges in device-edge systems due to resource limitations and communication overhead. To address these issues, collaborative…

Signal Processing · Electrical Eng. & Systems 2025-07-18 Jiahong Ning , Ce Zheng , Tingting Yang

Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency on edge devices. In…

Machine Learning · Computer Science 2023-06-26 Ziyang Zhang , Yang Zhao , Huan Li , Changyao Lin , Jie Liu

Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Théophane Vallaeys , Jakob Verbeek , Matthieu Cord

With the rapid advancement of diffusion-based generative models, Stable Diffusion (SD) has emerged as a state-of-the-art framework for high-fidelity im-age synthesis. However, existing SD models suffer from suboptimal feature aggregation,…

Graphics · Computer Science 2025-07-21 Zhen-Qi Chen , Yuan-Fu Yang

Generative models have increasingly impacted various tasks, from computer vision to interior design and beyond. Stable Diffusion, a powerful diffusion model, enables the creation of high-resolution images with intricate details from text…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Boyang Deng

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Robin Rombach , Andreas Blattmann , Dominik Lorenz , Patrick Esser , Björn Ommer