English
Related papers

Related papers: ResDiT: Evoking the Intrinsic Resolution Scalabili…

200 papers

Diffusion Transformers (DiTs) are a dominant backbone for high-fidelity text-to-image generation due to strong scalability and alignment at high resolutions. However, quadratic self-attention over dense spatial tokens leads to high…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Xuanhua Yin , Chuanzhi Xu , Haoxian Zhou , Boyu Wei , Weidong Cai

Diffusion models have revolutionized text-to-image (T2I) synthesis, producing high-quality, photorealistic images. However, they still struggle to properly render the spatial relationships described in text prompts. To address the lack of…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Andrea Rigo , Luca Stornaiuolo , Mauro Martino , Bruno Lepri , Nicu Sebe

This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image synthesis -- specifically, the deep fusion of large language…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Bingda Tang , Boyang Zheng , Xichen Pan , Sayak Paul , Saining Xie

This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Zhaoqing Wang , Xiaobo Xia , Runnan Chen , Dongdong Yu , Changhu Wang , Mingming Gong , Tongliang Liu

Recent multimodal face generation models address the spatial control limitations of text-to-image diffusion models by augmenting text-based conditioning with spatial priors such as segmentation masks, sketches, or edge maps. This multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Bharath Krishnamurthy , Ajita Rattani

Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Qingji Dong , Hang Dong , Mingqin Chen , Rui Zhang , Yitong Wang

Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Zheyuan Liu , Munan Ning , Qihui Zhang , Shuo Yang , Zhongrui Wang , Yiwei Yang , Xianzhe Xu , Yibing Song , Weihua Chen , Fan Wang , Li Yuan

Recent advancements in diffusion models have significantly improved performance in super-resolution (SR) tasks. However, previous research often overlooks the fundamental differences between SR and general image generation. General image…

Image and Video Processing · Electrical Eng. & Systems 2024-10-31 Hanlin Wu , Jiangwei Mo , Xiaohui Sun , Jie Ma

To overcome inherent hardware limitations of hyperspectral imaging systems with respect to their spatial resolution, fusion-based hyperspectral image (HSI) super-resolution is attracting increasing attention. This technique aims to fuse a…

Image and Video Processing · Electrical Eng. & Systems 2022-01-25 Xiuheng Wang , Jie Chen , Cédric Richard

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Chenhao Xu , Chang-Tsun Li , Chee Peng Lim , Douglas Creighton

Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yang Zheng , Wen Li , Zhaoqiang Liu

Diffusion models have achieved remarkable progress across various visual generation tasks. However, their performance significantly declines when generating content at resolutions higher than those used during training. Although numerous…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Zhen Yang , Guibao Shen , Minyang Li , Liang Hou , Mushui Liu , Luozhou Wang , Xin Tao , Ying-Cong Chen

Despite the significant advancements made by Diffusion Transformer (DiT)-based methods in video generation, there remains a notable gap with controllable camera pose perspectives. Existing works such as OpenSora do NOT adhere precisely to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yuelei Wang , Jian Zhang , Pengtao Jiang , Hao Zhang , Jinwei Chen , Bo Li

We present Scalable Interpolant Transformers (SiT), a family of generative models built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which allows for connecting two distributions in a more flexible way than…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Nanye Ma , Mark Goldstein , Michael S. Albergo , Nicholas M. Boffi , Eric Vanden-Eijnden , Saining Xie

Recent studies have introduced a new class of generative models for synthesizing implicit neural representations (INRs) that capture arbitrary continuous signals in various domains. These models opened the door for domain-agnostic…

Machine Learning · Computer Science 2024-03-21 Dogyun Park , Sihyeon Kim , Sojin Lee , Hyunwoo J. Kim

In this study, we delve into the generation of high-resolution images from pre-trained diffusion models, addressing persistent challenges, such as repetitive patterns and structural distortions, that emerge when models are applied beyond…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Linjiang Huang , Rongyao Fang , Aiping Zhang , Guanglu Song , Si Liu , Yu Liu , Hongsheng Li

Diffusion Transformer (DiT) models excel at generating high-quality images through iterative denoising steps, but serving them under strict Service Level Objectives (SLOs) is challenging due to their high computational cost, particularly at…

Machine Learning · Computer Science 2026-01-19 Runyu Lu , Shiqi He , Wenxuan Tan , Shenggui Li , Ruofan Wu , Jeff J. Ma , Ang Chen , Mosharaf Chowdhury

Diffusion transformers (DiT) have already achieved appealing synthesis and scaling properties in content recreation, e.g., image and video generation. However, scaling laws of DiT are less explored, which usually offer precise predictions…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Zhengyang Liang , Hao He , Ceyuan Yang , Bo Dai

Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Sihyun Yu , Sangkyung Kwak , Huiwon Jang , Jongheon Jeong , Jonathan Huang , Jinwoo Shin , Saining Xie

Transformer-based approaches have achieved superior performance in image restoration, since they can model long-term dependencies well. However, the limitation in capturing local information restricts their capacity to remove degradations.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Shihao Zhou , Duosheng Chen , Jinshan Pan , Jufeng Yang
‹ Prev 1 4 5 6 7 8 10 Next ›