English
Related papers

Related papers: CleanDIFT: Diffusion Features without Noise

200 papers

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Qi Wu , Mingyan Han , Ting Jiang , Chengzhi Jiang , Jinting Luo , Man Jiang , Haoqiang Fan , Shuaicheng Liu

In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in…

Image and Video Processing · Electrical Eng. & Systems 2024-09-18 Ryugo Morita , Hitoshi Nishimura , Ko Watanabe , Andreas Dengel , Jinjia Zhou

Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance.…

Image and Video Processing · Electrical Eng. & Systems 2022-03-22 Hyungjin Chung , Byeongsu Sim , Jong Chul Ye

We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Burak Can Biner , Farrin Marouf Sofian , Umur Berkay Karakaş , Duygu Ceylan , Erkut Erdem , Aykut Erdem

Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-30 Yang Yang , Yunpeng Li , George Sung , Shao-Fu Shih , Craig Dooley , Alessio Centazzo , Ramanan Rajeswaran

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Zhong Ji , Weilong Cao , Yan Zhang , Yanwei Pang , Jungong Han , Xuelong Li

This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval methods struggle in zero-shot settings due to the absence of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Hang Cheng , Fanhe Dong , Long Zeng

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…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Guillaume Couairon , Jakob Verbeek , Holger Schwenk , Matthieu Cord

Currently, applying diffusion models in pixel space of high resolution images is difficult. Instead, existing approaches focus on diffusion in lower dimensional spaces (latent diffusion), or have multiple super-resolution levels of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Emiel Hoogeboom , Jonathan Heek , Tim Salimans

Incorporating diffusion models in the image compression domain has the potential to produce realistic and detailed reconstructions, especially at extremely low bitrates. Previous methods focus on using diffusion models as expressive…

Image and Video Processing · Electrical Eng. & Systems 2024-10-10 Lucas Relic , Roberto Azevedo , Markus Gross , Christopher Schroers

We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by finding a better architecture through a series of ablations. For…

Machine Learning · Computer Science 2021-06-02 Prafulla Dhariwal , Alex Nichol

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

Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, these methods can sometimes be inadequate, resulting in…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-17 Sirui Li , Shuai Wang , Zhijun Liu , Zhongjie Jiang , Yannan Wang , Haizhou Li

We analyze, theoretically and empirically, the performance of generative diffusion models based on \emph{blind denoisers}, in which the denoiser is not given the noise amplitude in either the training or sampling processes. Assuming that…

Machine Learning · Computer Science 2026-02-11 Zahra Kadkhodaie , Aram-Alexandre Pooladian , Sinho Chewi , Eero Simoncelli

Given a style-reference image as the additional image condition, text-to-image diffusion models have demonstrated impressive capabilities in generating images that possess the content of text prompts while adopting the visual style of the…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Lin Zhu , Xinbing Wang , Chenghu Zhou , Qinying Gu , Nanyang Ye

Diffusion models have achieved state-of-the-art synthesis quality on both visual and audio tasks, and recent works further adapt them to textual data by diffusing on the embedding space. In this paper, we conduct systematic studies of the…

Computation and Language · Computer Science 2024-04-23 Zhujin Gao , Junliang Guo , Xu Tan , Yongxin Zhu , Fang Zhang , Jiang Bian , Linli Xu

Diffusion models have become fundamental tools for modeling data distributions in machine learning. Despite their success, these models face challenges when generating data with extreme brightness values, as evidenced by limitations…

Machine Learning · Statistics 2026-04-10 Takuro Kutsuna

Diffusion models have found phenomenal success as expressive priors for solving inverse problems, but their extension beyond natural images to more structured scientific domains remains limited. Motivated by applications in materials…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Timofey Efimov , Harry Dong , Megna Shah , Jeff Simmons , Sean Donegan , Yuejie Chi

Unseen noise signal which is not considered in a model training process is difficult to anticipate and would lead to performance degradation. Various methods have been investigated to mitigate unseen noise. In our previous work, an…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-24 Donghyeon Kim , Gwantae Kim , Bokyeung Lee , Jeong-gi Kwak , David K. Han , Hanseok Ko

Denoising diffusion models are widely used for high-quality image and video generation. Their performance depends on noise schedules, which define the distribution of noise levels applied during training and the sequence of noise levels…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Carlos Esteves , Ameesh Makadia