中文
相关论文

相关论文: Corruption-Aware Training of Latent Video Diffusio…

200 篇论文

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

计算机视觉与模式识别 · 计算机科学 2023-12-29 Andreas Blattmann , Robin Rombach , Huan Ling , Tim Dockhorn , Seung Wook Kim , Sanja Fidler , Karsten Kreis

We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. Recently, latent diffusion models trained for 2D image synthesis have been turned into…

Latent Diffusion Models (LDMs) are renowned for their powerful capabilities in image and video synthesis. Yet, compared to text-to-image (T2I) editing, text-to-video (T2V) editing suffers from a lack of decent temporal consistency and…

计算机视觉与模式识别 · 计算机科学 2024-10-10 Tianyi Lu , Xing Zhang , Jiaxi Gu , Renjing Pei , Songcen Xu , Xingjun Ma , Hang Xu , Zuxuan Wu

By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion…

机器学习 · 计算机科学 2025-04-02 Bac Nguyen , Chieh-Hsin Lai , Yuhta Takida , Naoki Murata , Toshimitsu Uesaka , Stefano Ermon , Yuki Mitsufuji

Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the training dynamics of DMs and observe an unanticipated phenomenon:…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Xiaoyu Wu , Jiaru Zhang , Yang Hua , Bohan Lyu , Hao Wang , Tao Song , Haibing Guan

Video diffusion models (VDMs) perform attention computation over the 3D spatio-temporal domain. Compared to large language models (LLMs) processing 1D sequences, their memory consumption scales cubically, necessitating parallel serving…

分布式、并行与集群计算 · 计算机科学 2025-12-09 Zhiyuan Wu , Shuai Wang , Li Chen , Kaihui Gao , Dan Li , Yanyu Ren , Qiming Zhang , Yong Wang

Temporally consistent video-to-video generation is critical for applications such as style transfer and upsampling. In this paper, we provide a theoretical analysis of warped noise - a recently proposed technique for training video…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Chao Liu , Arash Vahdat

Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more efficient processing at reduced computational costs. However,…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Jason Becker , Chris Wendler , Peter Baylies , Robert West , Christian Wressnegger

Ultrasound video classification enables automated diagnosis and has emerged as an important research area. However, publicly available ultrasound video datasets remain scarce, hindering progress in developing effective video classification…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Tingxiu Chen , Yilei Shi , Zixuan Zheng , Bingcong Yan , Jingliang Hu , Xiao Xiang Zhu , Lichao Mou

Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with…

计算机视觉与模式识别 · 计算机科学 2024-10-31 Hao Chen , Yujin Han , Diganta Misra , Xiang Li , Kai Hu , Difan Zou , Masashi Sugiyama , Jindong Wang , Bhiksha Raj

End-to-end audio-conditioned latent diffusion models (LDMs) have been widely adopted for audio-driven portrait animation, demonstrating their effectiveness in generating lifelike and high-resolution talking videos. However, direct…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Chunyu Li , Chao Zhang , Weikai Xu , Jingyu Lin , Jinghui Xie , Weiguo Feng , Bingyue Peng , Cunjian Chen , Weiwei Xing

We introduce the Joint Video-Image Diffusion model (JVID), a novel approach to generating high-quality and temporally coherent videos. We achieve this by integrating two diffusion models: a Latent Image Diffusion Model (LIDM) trained on…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Hadrien Reynaud , Matthew Baugh , Mischa Dombrowski , Sarah Cechnicka , Qingjie Meng , Bernhard Kainz

Latent Diffusion models (LDMs) have achieved remarkable results in synthesizing high-resolution images. However, the iterative sampling process is computationally intensive and leads to slow generation. Inspired by Consistency Models (song…

计算机视觉与模式识别 · 计算机科学 2023-10-09 Simian Luo , Yiqin Tan , Longbo Huang , Jian Li , Hang Zhao

Despite the remarkable progress in deep generative models, synthesizing high-resolution and temporally coherent videos still remains a challenge due to their high-dimensionality and complex temporal dynamics along with large spatial…

计算机视觉与模式识别 · 计算机科学 2023-03-31 Sihyun Yu , Kihyuk Sohn , Subin Kim , Jinwoo Shin

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

计算机视觉与模式识别 · 计算机科学 2022-04-14 Robin Rombach , Andreas Blattmann , Dominik Lorenz , Patrick Esser , Björn Ommer

Rapid advancements in video diffusion models have enabled the creation of realistic videos, raising concerns about unauthorized use and driving the demand for techniques to protect model ownership. Existing watermarking methods, while…

计算机视觉与模式识别 · 计算机科学 2025-03-31 MinHyuk Jang , Youngdong Jang , JaeHyeok Lee , Feng Yang , Gyeongrok Oh , Jongheon Jeong , Sangpil Kim

Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Shivam Duggal , Xingjian Bai , Zongze Wu , Richard Zhang , Eli Shechtman , Antonio Torralba , Phillip Isola , William T. Freeman

Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to perturbations poses a significant threat to their reliability in real-world applications. Despite often being…

计算机视觉与模式识别 · 计算机科学 2025-06-05 Jia Fu , Yongtao Wu , Yihang Chen , Kunyu Peng , Xiao Zhang , Volkan Cevher , Sepideh Pashami , Anders Holst

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
‹ 上一页 1 2 3 10 下一页 ›