English
Related papers

Related papers: From Sketch to Fresco: Efficient Diffusion Transfo…

200 papers

We propose in this paper an analytically new construct of a diffusion model whose drift and diffusion parameters yield an exponentially time-decaying Signal to Noise Ratio in the forward process. In reverse, the construct cleverly carries…

Image and Video Processing · Electrical Eng. & Systems 2024-08-16 Tanmay Asthana , Yufang Bao , Hamid Krim

The latest advances in artificial intelligence (AI) present many unprecedented opportunities to achieve much improved bandwidth saving in communications. Unlike conventional communication systems focusing on packet transport, rich datasets…

Machine Learning · Computer Science 2023-12-07 Achintha Wijesinghe , Songyang Zhang , Suchinthaka Wanninayaka , Weiwei Wang , Zhi Ding

The diffusion model has demonstrated promising results in image generation, recently becoming mainstream and representing a notable advancement for many generative modeling tasks. Prior applications of the diffusion model for both fast…

Instrumentation and Detectors · Physics 2025-06-18 Cheng Jiang , Sitian Qian , Huilin Qu

We introduce DiffFNO, a novel diffusion framework for arbitrary-scale super-resolution strengthened by a Weighted Fourier Neural Operator (WFNO). Mode Rebalancing in WFNO effectively captures critical frequency components, significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Xiaoyi Liu , Hao Tang

Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new…

Machine Learning · Computer Science 2023-06-01 Yang Song , Prafulla Dhariwal , Mark Chen , Ilya Sutskever

Diffusion models achieve superior performance in image generation tasks. However, it incurs significant computation overheads due to its iterative structure. To address these overheads, we analyze this iterative structure and observe that…

Hardware Architecture · Computer Science 2025-01-22 Sungbin Kim , Hyunwuk Lee , Wonho Cho , Mincheol Park , Won Woo Ro

Diffusion-based image super-resolution (SR) models have attracted substantial interest due to their powerful image restoration capabilities. However, prevailing diffusion models often struggle to strike an optimal balance between efficiency…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Qinpeng Cui , Yixuan Liu , Xinyi Zhang , Qiqi Bao , Qingmin Liao , Li Wang , Tian Lu , Zicheng Liu , Zhongdao Wang , Emad Barsoum

Pre-trained text-to-image (T2I) diffusion models have shown strong potential for real-world image super-resolution (Real-ISR), owing to their noise-started generation process that enables realistic texture synthesis and captures the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Wei Zhu , Kai Zhang , Yu Zheng , Lei Luo , Yong Guo , Jian Yang

Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance. However, the increased…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Pratheba Selvaraju , Tianyu Ding , Tianyi Chen , Ilya Zharkov , Luming Liang

Diffusion transformers have gained significant attention in recent years for their ability to generate high-quality images and videos, yet still suffer from a huge computational cost due to their iterative denoising process. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Zhixin Zheng , Xinyu Wang , Chang Zou , Shaobo Wang , Linfeng Zhang

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Xinwan Wen , Bowen Li , Jiajun Luo , Ye Li , Zhi Wang

Score distillation sampling (SDS) has emerged as an effective framework in text-driven 3D editing tasks, leveraging diffusion models for 3D-consistent editing. However, existing SDS-based 3D editing methods suffer from long training times…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Jiwook Kim , Seonho Lee , Jaeyo Shin , Jiho Choi , Hyunjung Shim

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Computation and Language · Computer Science 2026-03-06 Jia-Nan Li , Jian Guan , Wei Wu , Chongxuan Li

Diffusion Probabilistic Models stand as a critical tool in generative modelling, enabling the generation of complex data distributions. This family of generative models yields record-breaking performance in tasks such as image synthesis,…

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Hongjian Liu , Qingsong Xie , TianXiang Ye , Zhijie Deng , Chen Chen , Shixiang Tang , Xueyang Fu , Haonan Lu , Zheng-jun Zha

A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. Existing acceleration algorithms simplify the sampling by skipping most steps yet exhibit…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Mengfei Xia , Yujun Shen , Changsong Lei , Yu Zhou , Ran Yi , Deli Zhao , Wenping Wang , Yong-Jin Liu

Diffusion models have achieved remarkable success in image generation, yet their deployment remains constrained by the heavy computational cost and the need for numerous inference steps. Previous efforts on fewer-step distillation attempt…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Zhuobai Dong , Rui Zhao , Songjie Wu , Junchao Yi , Linjie Li , Zhengyuan Yang , Lijuan Wang , Alex Jinpeng Wang

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Shuning Chang , Pichao Wang , Jiasheng Tang , Fan Wang , Yi Yang

Diffusion- and flow-based models have advanced Real-world Image Super-Resolution (Real-ISR), but their multi-step sampling makes inference slow and hard to deploy. One-step distillation alleviates the cost, yet often degrades restoration…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Ruiqing Wang , Kai Zhang , Yuanzhi Zhu , Hanshu Yan , Shilin Lu , Jian Yang

Thanks to the powerful generative capacity of diffusion models, recent years have witnessed rapid progress in human motion generation. Existing diffusion-based methods employ disparate network architectures and training strategies. The…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Yiheng Huang , Hui Yang , Chuanchen Luo , Yuxi Wang , Shibiao Xu , Zhaoxiang Zhang , Man Zhang , Junran Peng