中文
相关论文

相关论文: Optimal Transport for Rectified Flow Image Editing…

200 篇论文

Aerodynamic inverse design can improve vehicle and aircraft efficiency, but practical design rarely seeks performance alone: vehicle refinement must reduce drag while preserving visual features linked to design language, brand recognition…

机器学习 · 计算机科学 2026-05-29 Huaguan Chen , Ning Lin , Luxi Chen , Jiacheng Cen , Rui Zhang , Wenbing Huang , Chongxuan Li , Hao Sun

We introduce the Approximated Optimal Transport (AOT) technique, a novel training scheme for diffusion-based generative models. Our approach aims to approximate and integrate optimal transport into the training process, significantly…

计算机视觉与模式识别 · 计算机科学 2024-03-11 Daegyu Kim , Jooyoung Choi , Chaehun Shin , Uiwon Hwang , Sungroh Yoon

Face editing methods, essential for tasks like virtual avatars, digital human synthesis and identity preservation, have traditionally been built upon GAN-based techniques, while recent focus has shifted to diffusion-based models due to…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Mengting Wei , Tuomas Varanka , Yante Li , Xingxun Jiang , Huai-Qian Khor , Guoying Zhao

Recently, diffusion models have gained popularity and attention in trajectory optimization due to their capability of modeling multi-modal probability distributions. However, addressing nonlinear equality constraints, i.e, dynamic…

机器人学 · 计算机科学 2026-03-10 Jushan Chen , Santiago Paternain

Finding an initial noise vector that produces an input image when fed into the diffusion process (known as inversion) is an important problem in denoising diffusion models (DDMs), with applications for real image editing. The…

计算机视觉与模式识别 · 计算机科学 2022-12-23 Bram Wallace , Akash Gokul , Nikhil Naik

Recently, text-to-image (T2I) editing has been greatly pushed forward by applying diffusion models. Despite the visual promise of the generated images, inconsistencies with the expected textual prompt remain prevalent. This paper aims to…

计算机视觉与模式识别 · 计算机科学 2024-09-20 Aoxue Li , Mingyang Yi , Zhenguo Li

Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Bo Li , Tingting Bao , Lingling Zhang , Weiping Fu , Yaxian Wang , Jun Liu

High-fidelity and controllable 3D simulation is essential for addressing the long-tail data scarcity in Autonomous Driving (AD), yet existing methods struggle to simultaneously achieve photorealistic rendering and interactive traffic…

计算机视觉与模式识别 · 计算机科学 2025-12-29 Zhiyuan Liu , Daocheng Fu , Pinlong Cai , Lening Wang , Ying Liu , Yilong Ren , Botian Shi , Jianqiang Wang

Large-scale text-to-image diffusion models, while powerful, suffer from prohibitive computational cost. Existing one-shot network pruning methods can hardly be directly applied to them due to the iterative denoising nature of diffusion…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Junhan Zhu , Hesong Wang , Mingluo Su , Zefang Wang , Huan Wang

We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-point-inspired iterative approach to invert real-world images,…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Yan Zheng , Zhenxiao Liang , Xiaoyan Cong , Lanqing guo , Yuehao Wang , Peihao Wang , Zhangyang Wang

We propose a diffusion-based framework for zero-shot image editing that unifies text-guided and reference-guided approaches without requiring fine-tuning. Our method leverages diffusion inversion and timestep-specific null-text embeddings…

计算机视觉与模式识别 · 计算机科学 2025-05-21 Dasol Jeong , Donggoo Kang , Jiwon Park , Hyebean Lee , Joonki Paik

Long-form video editing poses unique challenges due to the exponential increase in the computational cost from joint editing and Denoising Diffusion Implicit Models (DDIM) inversion across extended sequences. To address these limitations,…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Mustafa Munir , Md Mostafijur Rahman , Kartikeya Bhardwaj , Paul Whatmough , Radu Marculescu

Diffusion models have shown great promise in text-guided image style transfer, but there is a trade-off between style transformation and content preservation due to their stochastic nature. Existing methods require computationally expensive…

计算机视觉与模式识别 · 计算机科学 2023-04-13 Serin Yang , Hyunmin Hwang , Jong Chul Ye

The diffusion model has demonstrated superior performance in synthesizing diverse and high-quality images for text-guided image translation. However, there remains room for improvement in both the formulation of text prompts and the…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Qi Si , Bo Wang , Zhao Zhang

We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing diffusion-based editing methods often struggle to maintain…

Deep learning-based image restoration methods generally struggle with faithfully preserving the structures of the original image. In this work, we propose a novel Residual-Conditioned Optimal Transport (RCOT) approach, which models image…

计算机视觉与模式识别 · 计算机科学 2024-05-14 Xiaole Tang , Xin Hu , Xiang Gu , Jian Sun

In this paper, we introduce Geometry-Inverse-Meet-Pixel-Insert, short for GEO, an exceptionally versatile image editing technique designed to cater to customized user requirements at both local and global scales. Our approach seamlessly…

计算机视觉与模式识别 · 计算机科学 2024-09-19 Yan Zheng , Lemeng Wu

Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation. The fused image is expected to preserve fine details and maintain high visual fidelity. While diffusion models…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Xingxin Xu , Bing Cao , DongDong Li , Qinghua Hu , Pengfei Zhu

In this work, we propose Image-to-Image Rectified Flow Reformulation (I2I-RFR), a practical plug-in reformulation that recasts standard I2I regression networks as continuous-time transport models. While pixel-wise I2I regression is simple,…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Satoshi Iizuka , Shun Okamoto , Kazuhiro Fukui

Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application scope compared to traditional fixed-category segmentation tasks. Recent studies have…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Zishen Qu , Xuesong Li , Haijian Gu , Hongwei Kang , Quan Meng , Tianrui Niu , Xin Yang , Ruidong Pan