中文
相关论文

相关论文: CARE-Edit: Condition-Aware Routing of Experts for …

200 篇论文

Diffusion models have emerged as mainstream framework in visual generation. Building upon this success, the integration of Mixture of Experts (MoE) methods has shown promise in enhancing model scalability and performance. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2025-06-13 Yike Yuan , Ziyu Wang , Zihao Huang , Defa Zhu , Xun Zhou , Jingyi Yu , Qiyang Min

Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language models (LLMs), existing attempts to apply MoE to Diffusion…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Yujie Wei , Shiwei Zhang , Hangjie Yuan , Yujin Han , Zhekai Chen , Jiayu Wang , Difan Zou , Xihui Liu , Yingya Zhang , Yu Liu , Hongming Shan

Multi-object editing aims to modify multiple objects or regions in complex scenes while preserving structural coherence. This task faces significant challenges in scenarios involving overlapping or interacting objects: (1) Inaccurate…

计算机视觉与模式识别 · 计算机科学 2025-05-13 Hongyang Zhu , Haipeng Liu , Bo Fu , Yang Wang

Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However,…

计算机视觉与模式识别 · 计算机科学 2024-10-25 Rohit Gandikota , Hadas Orgad , Yonatan Belinkov , Joanna Materzyńska , David Bau

Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned…

计算机视觉与模式识别 · 计算机科学 2022-10-21 Guillaume Couairon , Jakob Verbeek , Holger Schwenk , Matthieu Cord

Diffusion models have emerged as a powerful generative technology and have been found to be applicable in various scenarios. Most existing foundational diffusion models are primarily designed for text-guided visual generation and do not…

计算机视觉与模式识别 · 计算机科学 2024-11-06 Zhen Han , Zeyinzi Jiang , Yulin Pan , Jingfeng Zhang , Chaojie Mao , Chenwei Xie , Yu Liu , Jingren Zhou

Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…

计算机视觉与模式识别 · 计算机科学 2024-12-06 Enis Simsar , Alessio Tonioni , Yongqin Xian , Thomas Hofmann , Federico Tombari

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Pengzhi Li , QInxuan Huang , Yikang Ding , Zhiheng Li

Recent diffusion-based image editing approaches have exhibited impressive editing capabilities in images with simple compositions. However, localized editing in complex scenarios has not been well-studied in the literature, despite its…

计算机视觉与模式识别 · 计算机科学 2023-12-22 Qi Mao , Lan Chen , Yuchao Gu , Zhen Fang , Mike Zheng Shou

Diffusion-based Image Editing has achieved significant success in recent years. However, it remains challenging to achieve high-quality image editing while maintaining the background similarity without sacrificing speed or memory…

图形学 · 计算机科学 2025-09-03 Siyi Liu , Weiming Chen , Yushun Tang , Zhihai He

A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However,…

计算机视觉与模式识别 · 计算机科学 2024-12-09 Senmao Li , Joost van de Weijer , Taihang Hu , Fahad Shahbaz Khan , Qibin Hou , Yaxing Wang , Jian Yang , Ming-Ming Cheng

Colour is one of the most perceptually salient yet least controllable attributes in image generation. Although recent diffusion models can modify object colours from user instructions, their results often deviate from the intended hue,…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Yuqi Yang , Dongliang Chang , Yijia Ling , Ruoyi Du , Zhanyu Ma

Diffusion-based editing has rapidly evolved from curated inpainting tools into general-purpose editors spanning text-guided instruction following, mask-localized edits, drag-based geometric manipulation, exemplar transfer, and training-free…

多媒体 · 计算机科学 2026-04-01 Yi Hu , Leying Yi , Emily Davis , Finn Carter

Diffusion-based Image Editing (DIE) is an emerging research hot-spot, which often applies a semantic mask to control the target area for diffusion-based editing. However, most existing solutions obtain these masks via manual operations or…

计算机视觉与模式识别 · 计算机科学 2024-01-24 Siyu Zou , Jiji Tang , Yiyi Zhou , Jing He , Chaoyi Zhao , Rongsheng Zhang , Zhipeng Hu , Xiaoshuai Sun

Diffusion Transformer models have significantly advanced image editing by encoding conditional images and integrating them into transformer layers. However, most edits involve modifying only small regions, while current methods uniformly…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Zhibin Qin , Zhenxiong Tan , Zeqing Wang , Songhua Liu , Xinchao Wang

While latent diffusion models achieve impressive image editing results, their application to iterative editing of the same image is severely restricted. When trying to apply consecutive edit operations using current models, they accumulate…

图形学 · 计算机科学 2025-04-29 Gal Almog , Ariel Shamir , Ohad Fried

Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-attention architectures offer no explicit channel telling the network where to apply the…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Honghao Cai , Xiangyuan Wang , Yunhao Bai , Haohua Chen , Tianze Zhou , Runqi Wang , Wei Zhu , Yibo Chen , Xu Tang , Yao Hu , Zhen Li

Domain expertise enhances judgment within boundaries but creates systematic vulnerabilities specifically at borders. We term this Transitive Expert Error (TEE), distinct from Dunning-Kruger effects, requiring calibrated expertise as…

人工智能 · 计算机科学 2026-01-09 Forest Mars

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade effects where initial…

机器学习 · 计算机科学 2026-03-16 Kevin Zhai , Sabbir Mollah , Zhenyi Wang , Mubarak Shah

Recent research has demonstrated that the combination of pretrained diffusion models with neural radiance fields (NeRFs) has emerged as a promising approach for text-to-3D generation. Simply coupling NeRF with diffusion models will result…

计算机视觉与模式识别 · 计算机科学 2023-06-19 Lu Yu , Wei Xiang , Kang Han
‹ 上一页 1 2 3 10 下一页 ›