中文
相关论文

相关论文: Erased, But Not Forgotten: Erased Rectified Flow T…

200 篇论文

Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is especially pronounced in emerging paradigms, such as Stable…

计算机视觉与模式识别 · 计算机科学 2025-01-03 Daiheng Gao , Shilin Lu , Shaw Walters , Wenbo Zhou , Jiaming Chu , Jie Zhang , Bang Zhang , Mengxi Jia , Jian Zhao , Zhaoxin Fan , Weiming Zhang

Removing undesired concepts from large-scale text-to-image (T2I) and text-to-video (T2V) diffusion models while preserving overall generative quality remains a major challenge, particularly as modern models such as Stable Diffusion v3,…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Zhaoxin Fan , Nanxiang Jiang , Daiheng Gao , Shiji Zhou , Wenjun Wu

Rectified Flow text-to-image models surpass diffusion models in image quality and text alignment, but adapting ReFlow for real-image editing remains challenging. We propose a new real-image editing method for ReFlow by analyzing the…

计算机视觉与模式识别 · 计算机科学 2025-07-03 Jimyeong Kim , Jungwon Park , Yeji Song , Nojun Kwak , Wonjong Rhee

Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures (e.g., Flux), this task remains under-explored in the recent…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Nanxiang Jiang , Zhaoxin Fan , Baisen Wang , Daiheng Gao , Junhang Cheng , Jifeng Guo , Yalan Qin , Yeying Jin , Hongwei Zheng , Faguo Wu , Wenjun Wu

Recent advances in diffusion transformers have shown remarkable generalization in visual synthesis, yet most dense perception methods still rely on text-to-image (T2I) generators designed for stochastic generation. We revisit this paradigm…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Yiqing Shi , Yiren Song , Mike Zheng Shou

Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyrighted styles, sensitive imagery, and harmful content raises…

计算机视觉与模式识别 · 计算机科学 2025-06-09 Changhoon Kim , Yanjun Qi

To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a complementary and…

计算机视觉与模式识别 · 计算机科学 2025-09-19 Ping Liu , Chi Zhang

Concept erasure techniques have been widely deployed in T2I diffusion models to prevent inappropriate content generation for safety and copyright considerations. However, as models evolve to next-generation architectures like Flux,…

机器学习 · 计算机科学 2025-10-07 Daiheng Gao , Nanxiang Jiang , Andi Zhang , Shilin Lu , Yufei Tang , Wenbo Zhou , Weiming Zhang , Zhaoxin Fan

Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for…

计算机视觉与模式识别 · 计算机科学 2025-07-17 Zixuan Fu , Yan Ren , Finn Carter , Chenyue Wang , Ze Niu , Dacheng Yu , Emily Davis , Bo Zhang

Editing real images using a pre-trained text-to-image (T2I) diffusion/flow model often involves inverting the image into its corresponding noise map. However, inversion by itself is typically insufficient for obtaining satisfactory results,…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Vladimir Kulikov , Matan Kleiner , Inbar Huberman-Spiegelglas , Tomer Michaeli

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

计算机视觉与模式识别 · 计算机科学 2024-05-01 Xiaoxuan Han , Songlin Yang , Wei Wang , Yang Li , Jing Dong

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications,…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Ouxiang Li , Yuan Wang , Xinting Hu , Houcheng Jiang , Yanbin Hao , Fuli Feng

Generative models transform random noise into images; their inversion aims to transform images back to structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of a real image using…

机器学习 · 计算机科学 2024-10-15 Litu Rout , Yujia Chen , Nataniel Ruiz , Constantine Caramanis , Sanjay Shakkottai , Wen-Sheng Chu

Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Chi Zhang , Changjia Zhu , Xiaowen Li , Yao Liu , Zhuo Lu

Erasing harmful or proprietary concepts from powerful text to image generators is an emerging safety requirement, yet current "concept erasure" techniques either collapse image quality, rely on brittle adversarial losses, or demand…

机器学习 · 计算机科学 2025-11-11 Abhiram Kusumba , Maitreya Patel , Kyle Min , Changhoon Kim , Chitta Baral , Yezhou Yang

Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow,…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Yingying Deng , Xiangyu He , Changwang Mei , Peisong Wang , Fan Tang

The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In response, concept erasure (defense) methods have been…

机器学习 · 计算机科学 2025-10-06 Alex D. Richardson , Kaicheng Zhang , Lucas Beerens , Dongdong Chen

The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyright-protected images, highlighting the need for effective safeguards within the models…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Chenyu Zhang

Style transfer, a pivotal task in image processing, synthesizes visually compelling images by seamlessly blending realistic content with artistic styles, enabling applications in photo editing and creative design. While mainstream…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Yingying Deng , Xiangyu He , Fan Tang , Weiming Dong , Xucheng Yin

Diffusion-based watermarking methods embed verifiable marks by manipulating the initial noise or the reverse diffusion trajectory. However, these methods share a critical assumption: verification can succeed only if the diffusion trajectory…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Rui Bao , Zheng Gao , Xiaoyu Li , Xiaoyan Feng , Yang Song , Jiaojiao Jiang
‹ 上一页 1 2 3 10 下一页 ›