中文
相关论文

相关论文: Couple to Control: Joint Initial Noise Design in D…

200 篇论文

Diffusion models have the ability to generate high quality images by denoising pure Gaussian noise images. While previous research has primarily focused on improving the control of image generation through adjusting the denoising process,…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Jiafeng Mao , Xueting Wang , Kiyoharu Aizawa

Diffusion models have emerged as powerful tools for generative tasks, producing high-quality outputs across diverse domains. However, how the generated data responds to the initial noise perturbation in diffusion models remains…

机器学习 · 计算机科学 2025-02-10 Bowen Song , Zecheng Zhang , Zhaoxu Luo , Jason Hu , Wei Yuan , Jing Jia , Zhengxu Tang , Guanyang Wang , Liyue Shen

Diffusion models that can generate high-quality data from randomly sampled Gaussian noises have become the mainstream generative method in both academia and industry. Are randomly sampled Gaussian noises equally good for diffusion models?…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Zipeng Qi , Lichen Bai , Haoyi Xiong , Zeke Xie

Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation. This continues to be a significant area of interest with the rise of new state-of-the-art methods…

计算机视觉与模式识别 · 计算机科学 2022-05-10 Vedant Singh , Surgan Jandial , Ayush Chopra , Siddharth Ramesh , Balaji Krishnamurthy , Vineeth N. Balasubramanian

Single-view novel view synthesis (NVS) models based on diffusion models have recently attracted increasing attention, as they can generate a series of novel view images from a single image prompt and camera pose information as conditions.…

计算机视觉与模式识别 · 计算机科学 2025-12-19 Zhihao Zhang , Xuejun Yang , Weihua Liu , Mouquan Shen

We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework, we observe that the underlying geometric structure is established during the early…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Jaeyoung Chung , Suyoung Lee , Kyoung Mu Lee

Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the diverse applications of…

计算机视觉与模式识别 · 计算机科学 2024-05-03 Xingchang Huang , Corentin Salaün , Cristina Vasconcelos , Christian Theobalt , Cengiz Öztireli , Gurprit Singh

Diffusion models have emerged as powerful generative frameworks, creating data samples by progressively denoising an initial random state. Traditionally, this initial state is sampled from a simple, fixed distribution like isotropic…

机器学习 · 计算机科学 2025-06-03 Zeming Li , Xiangyue Liu , Xiangyu Zhang , Ping Tan , Heung-Yeung Shum

Text-to-image diffusion models generate images by gradually converting white Gaussian noise into a natural image. White Gaussian noise is well suited for producing diverse outputs from a single text prompt due to its absence of structure.…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Nadav Z. Cohen , Ofir Abramovich , Ariel Shamir

Image noise can often be accurately fitted to a Poisson-Gaussian distribution. However, estimating the distribution parameters from a noisy image only is a challenging task. Here, we study the case when paired noisy and noise-free samples…

计算机视觉与模式识别 · 计算机科学 2022-12-29 Nicolas Bähler , Majed El Helou , Étienne Objois , Kaan Okumuş , Sabine Süsstrunk

Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underline noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with…

机器学习 · 计算机科学 2021-06-17 Eliya Nachmani , Robin San Roman , Lior Wolf

Diffusion models have achieved remarkable success in text-to-image generation tasks; however, the role of initial noise has been rarely explored. In this study, we identify specific regions within the initial noise image, termed trigger…

计算机视觉与模式识别 · 计算机科学 2024-06-05 Yuanhao Ban , Ruochen Wang , Tianyi Zhou , Boqing Gong , Cho-Jui Hsieh , Minhao Cheng

Diffusion models have emerged as a powerful framework for generative tasks in deep learning. They decompose generative modeling into two computational primitives: deterministic neural-network evaluation and stochastic sampling. Current…

机器学习 · 计算机科学 2026-03-31 Nihal Sanjay Singh , Mazdak Mohseni-Rajaee , Shaila Niazi , Kerem Y. Camsari

Diffusion models excel in generating high-quality images. However, current diffusion models struggle to produce reliable images without guidance methods, such as classifier-free guidance (CFG). Are guidance methods truly necessary?…

计算机视觉与模式识别 · 计算机科学 2024-12-06 Donghoon Ahn , Jiwon Kang , Sanghyun Lee , Jaewon Min , Minjae Kim , Wooseok Jang , Hyoungwon Cho , Sayak Paul , SeonHwa Kim , Eunju Cha , Kyong Hwan Jin , Seungryong Kim

Diffusion models for image generation function by progressively adding noise to an image set and training a model to separate out the signal from the noise. The noise profile used by these models is white noise -- that is, noise based on…

计算机视觉与模式识别 · 计算机科学 2025-07-09 Andrew Randono

Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compelling images. However, the imperative of achieving a seamless…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Xiefan Guo , Jinlin Liu , Miaomiao Cui , Jiankai Li , Hongyu Yang , Di Huang

In this paper, we address the problem of single-microphone speech separation in the presence of ambient noise. We propose a generative unsupervised technique that directly models both clean speech and structured noise components, training…

音频与语音处理 · 电气工程与系统科学 2025-09-19 Yochai Yemini , Rami Ben-Ari , Sharon Gannot , Ethan Fetaya

Recent image denoising methods have leveraged generative modeling for real noise synthesis to address the costly acquisition of real-world noisy data. However, these generative models typically require camera metadata and extensive…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Changjin Kim , HyeokJun Lee , YoungJoon Yoo

How do diffusion generative models convert pure noise into meaningful images? In a variety of pretrained diffusion models (including conditional latent space models like Stable Diffusion), we observe that the reverse diffusion process that…

计算机视觉与模式识别 · 计算机科学 2024-03-27 Binxu Wang , John J. Vastola

Single-channel audio separation aims to separate individual sources from a single-channel mixture. Most existing methods rely on supervised learning with synthetically generated paired data. However, obtaining high-quality paired data in…

音频与语音处理 · 电气工程与系统科学 2025-12-24 Runwu Shi , Chang Li , Jiang Wang , Rui Zhang , Nabeela Khan , Benjamin Yen , Takeshi Ashizawa , Kazuhiro Nakadai
‹ 上一页 1 2 3 10 下一页 ›