中文
相关论文

相关论文: The Evolving Nature of Latent Spaces: From GANs to…

200 篇论文

Latent space is one of the key concepts in generative AI, offering powerful means for creative exploration through vector manipulation. However, diffusion models like Stable Diffusion lack the intuitive latent vector control found in GANs,…

机器学习 · 计算机科学 2025-09-29 Zhihua Zhong , Xuanyang Huang

This paper examines three major generative modelling frameworks: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Stable Diffusion models. VAEs are effective at learning latent representations but frequently…

计算机视觉与模式识别 · 计算机科学 2024-08-19 Sanchayan Vivekananthan

Generative models serve as powerful tools for modeling the real world, with mainstream diffusion models, particularly those based on the latent diffusion model paradigm, achieving remarkable progress across various tasks, such as image and…

机器学习 · 计算机科学 2025-02-04 Wanghan Xu , Xiaoyu Yue , Zidong Wang , Yao Teng , Wenlong Zhang , Xihui Liu , Luping Zhou , Wanli Ouyang , Lei Bai

Diffusion-based generative models learn to iteratively transfer unstructured noise to a complex target distribution as opposed to Generative Adversarial Networks (GANs) or the decoder of Variational Autoencoders (VAEs) which produce samples…

机器学习 · 计算机科学 2022-10-26 Sarthak Mittal , Guillaume Lajoie , Stefan Bauer , Arash Mehrjou

Diffusion models are becoming increasingly popular in synthetic data generation and image editing applications. However, these models can amplify existing biases and propagate them to downstream applications. Therefore, it is crucial to…

计算机视觉与模式识别 · 计算机科学 2023-05-12 Malsha V. Perera , Vishal M. Patel

Recent advances in deep learning demonstrate the ability to generate synthetic gaze data. However, most approaches have primarily focused on generating data from random noise distributions or global, predefined latent embeddings, whereas…

人机交互 · 计算机科学 2025-11-14 Kamrul Hasan , Dmytro Katrychuk , Mehedi Hasan Raju , Oleg V. Komogortsev

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of…

机器学习 · 计算机科学 2023-10-31 Tianyang Hu , Fei Chen , Haonan Wang , Jiawei Li , Wenjia Wang , Jiacheng Sun , Zhenguo Li

Face recognition models are trained on large-scale datasets, which have privacy and ethical concerns. Lately, the use of synthetic data to complement or replace genuine data for the training of face recognition models has been proposed.…

计算机视觉与模式识别 · 计算机科学 2025-06-10 David Geissbühler , Hatef Otroshi Shahreza , Sébastien Marcel

The rapid advancement in image generation models has predominantly been driven by diffusion models, which have demonstrated unparalleled success in generating high-fidelity, diverse images from textual prompts. Despite their success,…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Yusuf Dalva , Hidir Yesiltepe , Pinar Yanardag

Despite the success of Generative Adversarial Networks (GANs) in image synthesis, there lacks enough understanding on what generative models have learned inside the deep generative representations and how photo-realistic images are able to…

计算机视觉与模式识别 · 计算机科学 2020-02-12 Ceyuan Yang , Yujun Shen , Bolei Zhou

Modern learning-based approaches to 3D-aware image synthesis achieve high photorealism and 3D-consistent viewpoint changes for the generated images. Existing approaches represent instances in a shared canonical space. However, for…

计算机视觉与模式识别 · 计算机科学 2024-04-15 Katja Schwarz , Seung Wook Kim , Jun Gao , Sanja Fidler , Andreas Geiger , Karsten Kreis

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

计算机视觉与模式识别 · 计算机科学 2026-01-23 Theodoros Kouzelis , Efstathios Karypidis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

The integration of generative AI in visual art has revolutionized not only how visual content is created but also how AI interacts with and reflects the underlying domain knowledge. This survey explores the emerging realm of diffusion-based…

人工智能 · 计算机科学 2024-08-23 Bingyuan Wang , Qifeng Chen , Zeyu Wang

Diffusion models have revolutionized generative modeling, enabling unprecedented realism in image and video synthesis. This success has sparked interest in leveraging their representations for visual understanding tasks. While recent works…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Pedro Vélez , Luisa F. Polanía , Yi Yang , Chuhan Zhang , Rishabh Kabra , Anurag Arnab , Mehdi S. M. Sajjadi

Generative AI models have revolutionized various fields by enabling the creation of realistic and diverse data samples. Among these models, diffusion models have emerged as a powerful approach for generating high-quality images, text, and…

计算机视觉与模式识别 · 计算机科学 2024-02-27 Gaurav Raut , Apoorv Singh

Generative artificial intelligence (AI) refers to algorithms that create synthetic but realistic output. Diffusion models currently offer state of the art performance in generative AI for images. They also form a key component in more…

机器学习 · 计算机科学 2023-12-27 Catherine F. Higham , Desmond J. Higham , Peter Grindrod

Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred…

机器学习 · 统计学 2017-12-13 Yoshihiro Nagano , Ryo Karakida , Masato Okada

Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for…

机器学习 · 计算机科学 2025-06-03 Magdalena Proszewska , Nikolay Malkin , N. Siddharth

Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…

计算机视觉与模式识别 · 计算机科学 2025-01-31 Fouad Bousetouane

Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image.…

计算机视觉与模式识别 · 计算机科学 2020-04-01 Yujun Shen , Jinjin Gu , Xiaoou Tang , Bolei Zhou
‹ 上一页 1 2 3 10 下一页 ›