中文
相关论文

相关论文: Vision-guided and Mask-enhanced Adaptive Denoising…

200 篇论文

In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and…

计算机视觉与模式识别 · 计算机科学 2022-08-24 Xing Nie , Bolin Ni , Jianlong Chang , Gaomeng Meng , Chunlei Huo , Zhaoxiang Zhang , Shiming Xiang , Qi Tian , Chunhong Pan

Recent advances in diffusion models have revolutionized text-guided image editing, yet existing editing methods face critical challenges in hyperparameter identification. To get the reasonable editing performance, these methods often…

计算机视觉与模式识别 · 计算机科学 2025-10-08 Chau Pham , Quan Dao , Mahesh Bhosale , Yunjie Tian , Dimitris Metaxas , David Doermann

Recent research has shown that large language models pretrained using unsupervised approaches can achieve significant performance improvement on many downstream tasks. Typically when adapting these language models to downstream tasks, like…

计算与语言 · 计算机科学 2022-06-08 Xiaodi Sun , Sunny Rajagopalan , Priyanka Nigam , Weiyi Lu , Yi Xu , Belinda Zeng , Trishul Chilimbi

With the great success of text-conditioned diffusion models in creative text-to-image generation, various text-driven image editing approaches have attracted the attentions of many researchers. However, previous works mainly focus on…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Zhiyuan Ma , Guoli Jia , Bowen Zhou

3D mask presentation attack detection is crucial for protecting face recognition systems against the rising threat of 3D mask attacks. While most existing methods utilize multimodal features or remote photoplethysmography (rPPG) signals to…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Fangling Jiang , Qi Li , Bing Liu , Weining Wang , Caifeng Shan , Zhenan Sun , Ming-Hsuan Yang

Image inpainting, the process of restoring missing or corrupted regions of an image by reconstructing pixel information, has recently seen considerable advancements through deep learning-based approaches. In this paper, we introduce a novel…

计算机视觉与模式识别 · 计算机科学 2024-11-11 Kourosh Kiani , Razieh Rastgoo , Alireza Chaji , Sergio Escalera

We present a simple but effective training-free approach for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our goal is to generate an image that aligns with the target task while preserving the…

计算机视觉与模式识别 · 计算机科学 2024-12-23 Hyunsoo Lee , Minsoo Kang , Bohyung Han

Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge of interest in the delicate refinement of text prompts.…

计算机视觉与模式识别 · 计算机科学 2024-04-08 Wenyi Mo , Tianyu Zhang , Yalong Bai , Bing Su , Ji-Rong Wen , Qing Yang

Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions.…

计算机视觉与模式识别 · 计算机科学 2025-05-26 Zhihua Liu , Amrutha Saseendran , Lei Tong , Xilin He , Fariba Yousefi , Nikolay Burlutskiy , Dino Oglic , Tom Diethe , Philip Teare , Huiyu Zhou , Chen Jin

Text-based semantic image editing assumes the manipulation of an image using a natural language instruction. Although recent works are capable of generating creative and qualitative images, the problem is still mostly approached as a black…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Maria Mihaela Trusca , Tinne Tuytelaars , Marie-Francine Moens

Diffusion models have significantly improved text-to-image generation, producing high-quality, realistic images from textual descriptions. Beyond generation, object-level image editing remains a challenging problem, requiring precise…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Marco Schouten , Mehmet Onurcan Kaya , Serge Belongie , Dim P. Papadopoulos

Recent advancements in diffusion models have significantly facilitated text-guided video editing. However, there is a relative scarcity of research on image-guided video editing, a method that empowers users to edit videos by merely…

计算机视觉与模式识别 · 计算机科学 2025-01-09 Zhi-Lin Huang , Yixuan Liu , Chujun Qin , Zhongdao Wang , Dong Zhou , Dong Li , Emad Barsoum

Text-driven video generation witnesses rapid progress. However, merely using text prompts is not enough to depict the desired subject appearance that accurately aligns with users' intents, especially for customized content creation. In this…

计算机视觉与模式识别 · 计算机科学 2023-12-04 Yuming Jiang , Tianxing Wu , Shuai Yang , Chenyang Si , Dahua Lin , Yu Qiao , Chen Change Loy , Ziwei Liu

This is the technique report for the winning solution of the CVPR2024 GenAI Media Generation Challenge Workshop's Instruction-guided Image Editing track. Instruction-guided image editing has been largely studied in recent years. The most…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Xuan Ju , Junhao Zhuang , Zhaoyang Zhang , Yuxuan Bian , Qiang Xu , Ying Shan

Inversion-based visual editing provides an effective and training-free way to edit an image or a video based on user instructions. Existing methods typically inject source image information during the sampling process to maintain editing…

计算机视觉与模式识别 · 计算机科学 2025-12-29 Zhi Ouyang , Dian Zheng , Xiao-Ming Wu , Jian-Jian Jiang , Kun-Yu Lin , Jingke Meng , Wei-Shi Zheng

Improper exposure often leads to severe loss of details, color distortion, and reduced contrast. Exposure correction still faces two critical challenges: (1) the ignorance of object-wise regional semantic information causes the color shift…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Puzhen Wu , Han Weng , Quan Zheng , Yi Zhan , Hewei Wang , Yiming Li , Jiahui Han , Rui Xu

As the field of image generation rapidly advances, traditional diffusion models and those integrated with multimodal large language models (LLMs) still encounter limitations in interpreting complex prompts and preserving image consistency…

计算机视觉与模式识别 · 计算机科学 2024-05-28 Xinyu Zhang , Mengxue Kang , Fei Wei , Shuang Xu , Yuhe Liu , Lin Ma

Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real…

计算机视觉与模式识别 · 计算机科学 2024-08-22 You-Ming Chang , Chen Yeh , Wei-Chen Chiu , Ning Yu

Taking inspiration from recent developments in visual generative tasks using diffusion models, we propose a method for end-to-end speech-driven video editing using a denoising diffusion model. Given a video of a talking person, and a…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Dan Bigioi , Shubhajit Basak , Michał Stypułkowski , Maciej Zięba , Hugh Jordan , Rachel McDonnell , Peter Corcoran

Inspired by the success of vision-language methods (VLMs) in zero-shot classification, recent works attempt to extend this line of work into object detection by leveraging the localization ability of pre-trained VLMs and generating pseudo…

计算机视觉与模式识别 · 计算机科学 2023-08-01 Yanxin Long , Jianhua Han , Runhui Huang , Xu Hang , Yi Zhu , Chunjing Xu , Xiaodan Liang