中文
相关论文

相关论文: Massive Activations are the Key to Local Detail Sy…

200 篇论文

Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood. In this work, we…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Evelyn Turri , Davide Bucciarelli , Sara Sarto , Lorenzo Baraldi , Marcella Cornia

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

Despite rapid progress in video diffusion transformers, how their internal model signals can be leveraged with minimal overhead to enhance video generation quality remains underexplored. In this work, we study the role of Massive…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Xianhang Cheng , Yujian Zheng , Zhenyu Xie , Tingting Liao , Hao Li

Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT) architecture. Existing attention manipulation methods focus exclusively on the Key…

计算机视觉与模式识别 · 计算机科学 2026-02-26 Guandong Li

Text-to-image generation models have achieved remarkable capabilities in synthesizing images, but often struggle to provide fine-grained control over the output. Existing guidance approaches, such as segmentation maps and depth maps,…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Sangmin Jung , Utkarsh Nath , Yezhou Yang , Giulia Pedrielli , Joydeep Biswas , Amy Zhang , Hassan Ghasemzadeh , Pavan Turaga

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 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

In autonomous driving, deep models have shown remarkable performance across various visual perception tasks with the demand of high-quality and huge-diversity training datasets. Such datasets are expected to cover various driving scenarios…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Jiahang Tu , Wei Ji , Hanbin Zhao , Chao Zhang , Roger Zimmermann , Hui Qian

Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively injecting local appearance into a DiT can disrupt its holistic…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Shengrong Gu , Ye Wang , Song Wu , Rui Ma , Qian Wang , Lanjun Wang , Zili Yi

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Yuxi Liu , Yipeng Hu , Zekun Zhang , Kunze Jiang , Kun Yuan

High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Minh Khoa Le , Kien Do , Duc Thanh Nguyen , Truyen Tran

Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…

计算机视觉与模式识别 · 计算机科学 2025-02-21 Vignesh Sundaresha

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

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

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 models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Lianghui Zhu , Zilong Huang , Bencheng Liao , Jun Hao Liew , Hanshu Yan , Jiashi Feng , Xinggang Wang

Recent breakthroughs in Diffusion Transformers (DiTs) have revolutionized the field of visual synthesis due to their superior scalability. To facilitate DiTs' capability of capturing meaningful internal representations, recent works such as…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Mengping Yang , Zhiyu Tan , Binglei Li , Xiaomeng Yang , Hesen Chen , Hao Li

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

While generative modeling on time series facilitates more capable and flexible probabilistic forecasting, existing generative time series models do not address the multi-dimensional properties of time series data well. The prevalent…

机器学习 · 计算机科学 2026-02-09 Haoran Zhang , Haixuan Liu , Yong Liu , Yunzhong Qiu , Yuxuan Wang , Jianmin Wang , Mingsheng Long

Personalized image generation aims to produce images of user-specified concepts while enabling flexible editing. Recent training-free approaches, while exhibit higher computational efficiency than training-based methods, struggle with…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Haoran Feng , Zehuan Huang , Lin Li , Hairong Lv , Lu Sheng
‹ 上一页 1 2 3 10 下一页 ›