English
Related papers

Related papers: Latent Swap Joint Diffusion for 2D Long-Form Laten…

200 papers

Deepfake technology, driven by Generative Adversarial Networks (GANs), poses significant risks to privacy and societal security. Existing detection methods are predominantly passive, focusing on post-event analysis without preventing…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Mengxiao Huang , Minglei Shu , Shuwang Zhou , Zhaoyang Liu

The success of the text-guided diffusion model has inspired the development and release of numerous powerful diffusion models within the open-source community. These models are typically fine-tuned on various expert datasets, showcasing…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Cong Wang , Kuan Tian , Yonghang Guan , Fei Shen , Zhiwei Jiang , Qing Gu , Jun Zhang

This paper presents a novel generative framework for learning shared latent representations across multimodal data. Many advanced multimodal methods focus on capturing all combinations of modality-specific details across inputs, which can…

Machine Learning · Computer Science 2025-08-26 Jiali Cui , Yan-Ying Chen , Yanxia Zhang , Matthew Klenk

Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Xichen Xu , Yanshu Wang , Jinbao Wang , Xiaoning Lei , Guoyang Xie , Guannan Jiang , Zhichao Lu

In this paper, we introduce a novel generative model, Diffusion Layout Transformers without Autoencoder (Dolfin), which significantly improves the modeling capability with reduced complexity compared to existing methods. Dolfin employs a…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Yilin Wang , Zeyuan Chen , Liangjun Zhong , Zheng Ding , Zhizhou Sha , Zhuowen Tu

Diffusion models have significantly advanced the state of the art in image, audio, and video generation tasks. However, their applications in practical scenarios are hindered by slow inference speed. Drawing inspiration from the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Chen Xu , Tianhui Song , Weixin Feng , Xubin Li , Tiezheng Ge , Bo Zheng , Limin Wang

Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges. Recent work, the masked autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Tiankai Hang , Jianmin Bao , Fangyun Wei , Dong Chen

Ultra-Wide-Field Fluorescein Angiography (UWF-FA) enables precise identification of ocular diseases using sodium fluorescein, which can be potentially harmful. Existing research has developed methods to generate UWF-FA from Ultra-Wide-Field…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Zhaojie Fang , Xiao Yu , Guanyu Zhou , Ke Zhuang , Yifei Chen , Ruiquan Ge , Changmiao Wang , Gangyong Jia , Qing Wu , Juan Ye , Maimaiti Nuliqiman , Peifang Xu , Ahmed Elazab

Deep fake technology became a hot field of research in the last few years. Researchers investigate sophisticated Generative Adversarial Networks (GAN), autoencoders, and other approaches to establish precise and robust algorithms for face…

Computer Vision and Pattern Recognition · Computer Science 2022-02-08 Daniil Chesakov , Anastasia Maltseva , Alexander Groshev , Andrey Kuznetsov , Denis Dimitrov

We present SPAD, a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation, we repurpose a pretrained 2D diffusion model by extending its self-attention layers with…

Computer Vision and Pattern Recognition · Computer Science 2024-02-09 Yash Kant , Ziyi Wu , Michael Vasilkovsky , Guocheng Qian , Jian Ren , Riza Alp Guler , Bernard Ghanem , Sergey Tulyakov , Igor Gilitschenski , Aliaksandr Siarohin

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

This paper presents StrADiff, a Structured Source-Wise Adaptive Diffusion Framework for unsupervised blind source separation under linear and nonlinear mixing. The framework treats each latent dimension as a source branch and assigns to it…

Machine Learning · Statistics 2026-04-29 Yuan-Hao Wei

Subject-driven image generation aims to synthesize novel depictions of a specific subject across diverse contexts while preserving its core identity features. Achieving both strong identity consistency and high prompt diversity presents a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Aditi Singhania , Arushi Jain , Krutik Malani , Riddhi Dhawan , Souymodip Chakraborty , Vineet Batra , Ankit Phogat

Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Tongcheng Fang , Hanling Zhang , Ruiqi Xie , Zhuo Han , Xin Tao , Tianchen Zhao , Pengfei Wan , Wenbo Ding , Wanli Ouyang , Xuefei Ning , Yu Wang

Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion…

Machine Learning · Computer Science 2026-05-25 Jean-Marie Lemercier , Tomas Geffner , Karsten Kreis , Morteza Mardani , Arash Vahdat , Ante Jukić

Diffusion models achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is an unresolved issue for diffusion-based image synthesis, particularly for synthesizing multiple…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Weimin Qiu , Jieke Wang , Meng Tang

Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as REPA (relying on external representation encoders) or SRA…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Mengmeng Wang , Dengyang Jiang , Liuzhuozheng Li , Yucheng Lin , Guojiang Shen , Xiangjie Kong , Yong Liu , Guang Dai , Jingdong Wang

We present SemLayoutDiff, a unified model for synthesizing diverse 3D indoor scenes across multiple room types. The model introduces a scene layout representation combining a top-down semantic map and attributes for each object. Unlike…

Graphics · Computer Science 2025-09-09 Xiaohao Sun , Divyam Goel , Angel X. Chang

Novel view synthesis (NVS) from a single image is highly ill-posed due to large unobserved regions, especially for views that deviate significantly from the input. While existing methods focus on consistency between the source and generated…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Xueyang Kang , Zhengkang Xiang , Zezheng Zhang , Kourosh Khoshelham

Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-27 Wen Huang , Yanmei Gu , Zhiming Wang , Huijia Zhu , Yanmin Qian