English
Related papers

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

200 papers

Diffusion Transformers (DiTs) achieve state-of-the-art results in text-to-image, text-to-video generation, and editing. However, their large model size and the quadratic cost of spatial-temporal attention over multiple denoising steps make…

Machine Learning · Computer Science 2025-09-24 Muhammad Adnan , Nithesh Kurella , Akhil Arunkumar , Prashant J. Nair

Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Henry Che , Jingkang Wang , Yun Chen , Ze Yang , Sivabalan Manivasagam , Raquel Urtasun

Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Xunnong Xu , Mengying Cao

Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a…

Computer Vision and Pattern Recognition · Computer Science 2022-12-02 Wan-Cyuan Fan , Yen-Chun Chen , Dongdong Chen , Yu Cheng , Lu Yuan , Yu-Chiang Frank Wang

Stochastic sampling techniques are ubiquitous in real-time rendering, where performance constraints force the use of low sample counts, leading to noisy intermediate results. To remove this noise, the post-processing step of temporal and…

Graphics · Computer Science 2023-10-25 William Donnelly , Alan Wolfe , Judith Bütepage , Jon Valdés

Generative diffusion models have emerged as a powerful tool for high-quality image synthesis, yet their iterative nature demands significant computational resources. This paper proposes an efficient time step sampling method based on an…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Haeil Lee , Hansang Lee , Seoyeon Gye , Junmo Kim

The workload of real-time rendering is steeply increasing as the demand for high resolution, high refresh rates, and high realism rises, overwhelming most graphics cards. To mitigate this problem, one of the most popular solutions is to…

Graphics · Computer Science 2023-10-17 Zhihua Zhong , Jingsen Zhu , Yuxin Dai , Chuankun Zheng , Yuchi Huo , Guanlin Chen , Hujun Bao , Rui Wang

This study presents a novel approach to enhance the cost-to-quality ratio of image generation with diffusion models. We hypothesize that differences between distilled (e.g. FLUX.1-schnell) and baseline (e.g. FLUX.1-dev) models are…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Jakub Wasala , Bartlomiej Wrzalski , Kornelia Noculak , Yuliia Tarasenko , Oliwer Krupa , Jan Kocon , Grzegorz Chodak

Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance, but it often fails to recover fine details because measurement terms are applied in a manner that is…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Feng Tian , Yixuan Li , Weili Zeng , Weitian Zhang , Yichao Yan , Xiaokang Yang

Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs and slow speeds. An intuitive solution involves adopting…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Xiang Wang , Shiwei Zhang , Hangjie Yuan , Yujie Wei , Yingya Zhang , Changxin Gao , Yuehuan Wang , Nong Sang

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Yasaman Haghighi , Alexandre Alahi

The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…

Hardware Architecture · Computer Science 2025-07-03 Zhican Wang , Guanghui He , Hongxiang Fan

Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent feature. However, a fundamental trade-off is inherent between…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Qingyu Shi , Size Wu , Jinbin Bai , Kaidong Yu , Yujing Wang , Yunhai Tong , Xiangtai Li , Xuelong Li

Dynamic urban scene modeling is a rapidly evolving area with broad applications. While current approaches leveraging neural radiance fields or Gaussian Splatting have achieved fine-grained reconstruction and high-fidelity novel view…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Yuru Xiao , Zihan Lin , Chao Lu , Deming Zhai , Kui Jiang , Wenbo Zhao , Wei Zhang , Junjun Jiang , Huanran Wang , Xianming Liu

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

Computation and Language · Computer Science 2023-10-27 Yongxin Zhu , Zhujin Gao , Xinyuan Zhou , Zhongyi Ye , Linli Xu

Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both…

Image and Video Processing · Electrical Eng. & Systems 2025-05-27 Zhiyuan Li , Yanhui Zhou , Hao Wei , Chenyang Ge , Ajmal Mian

Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric cases. In…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Yuanhao Cai , He Zhang , Kai Zhang , Yixun Liang , Mengwei Ren , Fujun Luan , Qing Liu , Soo Ye Kim , Jianming Zhang , Zhifei Zhang , Yuqian Zhou , Yulun Zhang , Xiaokang Yang , Zhe Lin , Alan Yuille

Both a high spatial and a high temporal resolution of images and videos are desirable in many applications such as entertainment systems, monitoring manufacturing processes, or video surveillance. Due to the limited throughput of pixels per…

Image and Video Processing · Electrical Eng. & Systems 2022-04-08 Markus Jonscher , Jürgen Seiler , Daniela Lanz , Michael Schöberl , Michel Bätz , André Kaup

Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-20 Chenyu Wang , Shuo Yan , Yixuan Chen , Yujiang Wang , Mingzhi Dong , Xiaochen Yang , Dongsheng Li , Robert P. Dick , Qin Lv , Fan Yang , Tun Lu , Ning Gu , Li Shang

Denoising Diffusion Models (DDMs) have become a popular tool for generating high-quality samples from complex data distributions. These models are able to capture sophisticated patterns and structures in the data, and can generate samples…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Emanuele Aiello , Diego Valsesia , Enrico Magli