中文
相关论文

相关论文: Few Channels Draw The Whole Picture: Revealing Mas…

200 篇论文

Pre-trained stable diffusion models (SD) have shown great advances in visual correspondence. In this paper, we investigate the capabilities of Diffusion Transformers (DiTs) for accurate dense correspondence. Distinct from SD, DiTs exhibit a…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Chaofan Gan , Yuanpeng Tu , Xi Chen , Tieyuan Chen , Yuxi Li , Mehrtash Harandi , Weiyao Lin

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for visual generation. Recent observations reveal \emph{Massive Activations} (MAs) in their internal feature maps, yet their function remains poorly understood. In…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Chaofan Gan , Zicheng Zhao , Yuanpeng Tu , Xi Chen , Ziran Qin , Tieyuan Chen , Mehrtash Harandi , Weiyao Lin

Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Jiayang Li , Chengjie Jiang , Junjun Jiang , Pengwei Liang , Jiayi Ma , Liqiang Nie

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Philipp Becker , Abhinav Mehrotra , Ruchika Chavhan , Malcolm Chadwick , Luca Morreale , Mehdi Noroozi , Alberto Gil Ramos , Sourav Bhattacharya

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic…

计算机视觉与模式识别 · 计算机科学 2024-10-21 Benyuan Meng , Qianqian Xu , Zitai Wang , Xiaochun Cao , Qingming Huang

Starting from flow- and diffusion-based transformers, Multi-modal Diffusion Transformers (MM-DiTs) have reshaped text-to-vision generation, gaining acclaim for exceptional visual fidelity. As these models advance, users continually push the…

人工智能 · 计算机科学 2025-10-07 Seil Kang , Woojung Han , Dayun Ju , Seong Jae Hwang

Diffusion Transformers (DiTs) have recently achieved remarkable success in text-guided image generation. In image editing, DiTs project text and image inputs to a joint latent space, from which they decode and synthesize new images.…

计算机视觉与模式识别 · 计算机科学 2024-11-14 Zitao Shuai , Chenwei Wu , Zhengxu Tang , Bowen Song , Liyue Shen

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Yuang Ai , Qihang Fan , Xuefeng Hu , Zhenheng Yang , Ran He , Huaibo Huang

Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Zitao Shuai , Chenwei Wu , Zhengxu Tang , Bowen Song , Liyue Shen

Current text-to-image diffusion generation typically employs complete-text conditioning. Due to the intricate syntax, diffusion transformers (DiTs) inherently suffer from a comprehension defect of complete-text captions. One-fly…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Yu Zhang , Jialei Zhou , Xinchen Li , Qi Zhang , Zhongwei Wan , Tianyu Wang , Duoqian Miao , Changwei Wang , Longbing Cao

Diffusion Transformers (DiTs) have greatly advanced text-to-image generation, but models still struggle to generate the correct spatial relations between objects as specified in the text prompt. In this study, we adopt a mechanistic…

人工智能 · 计算机科学 2026-04-07 Binxu Wang , Jingxuan Fan , Xu Pan

Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Weinan Jia , Mengqi Huang , Nan Chen , Lei Zhang , Zhendong Mao

Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention…

计算机视觉与模式识别 · 计算机科学 2025-07-03 Alec Helbling , Tuna Han Salih Meral , Ben Hoover , Pinar Yanardag , Duen Horng Chau

Diffusion models (DMs) embark a new era of generative modeling and offer more opportunities for efficient generating high-quality and realistic data samples. However, their widespread use has also brought forth new challenges in model…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Jingyao Xu , Yuetong Lu , Yandong Li , Siyang Lu , Dongdong Wang , Xiang Wei

Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net architectures, where…

图像与视频处理 · 电气工程与系统科学 2026-03-16 Junqi Shi , Ming Lu , Xingchen Li , Anle Ke , Ruiqi Zhang , Zhan Ma

We present OminiControl, a novel approach that rethinks how image conditions are integrated into Diffusion Transformer (DiT) architectures. Current image conditioning methods either introduce substantial parameter overhead or handle only…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Zhenxiong Tan , Songhua Liu , Xingyi Yang , Qiaochu Xue , Xinchao Wang

Diffusion models have become leading approaches for high-fidelity image generation. Recent DiT-based diffusion models, in particular, achieve strong prompt adherence while producing high-quality samples. We propose SHIFT, a simple but…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Nina Konovalova , Andrey Kuznetsov , Aibek Alanov

Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application suffers from inherent dynamic feature instability, leading…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Guanjie Chen , Xinyu Zhao , Yucheng Zhou , Xiaoye Qu , Tianlong Chen , Yu Cheng

Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Shuai Wang , Zhi Tian , Weilin Huang , Limin Wang

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Chen Chen , Rui Qian , Wenze Hu , Tsu-Jui Fu , Jialing Tong , Xinze Wang , Lezhi Li , Bowen Zhang , Alex Schwing , Wei Liu , Yinfei Yang
‹ 上一页 1 2 3 10 下一页 ›