English
Related papers

Related papers: CV-VAE: A Compatible Video VAE for Latent Generati…

200 papers

Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Pingyu Wu , Kai Zhu , Yu Liu , Liming Zhao , Wei Zhai , Yang Cao , Zheng-Jun Zha

Variational Autoencoder (VAE), compressing videos into latent representations, is a crucial preceding component of Latent Video Diffusion Models (LVDMs). With the same reconstruction quality, the more sufficient the VAE's compression for…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Liuhan Chen , Zongjian Li , Bin Lin , Bin Zhu , Qian Wang , Shenghai Yuan , Xing Zhou , Xinhua Cheng , Li Yuan

Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Yazhou Xing , Yang Fei , Yingqing He , Jingye Chen , Jiaxin Xie , Xiaowei Chi , Qifeng Chen

In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space. While existing video generative models apply fixed compression rates via…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Zhihang Yuan , Siyuan Wang , Rui Xie , Hanling Zhang , Tongcheng Fang , Yuzhang Shang , Shengen Yan , Guohao Dai , Yu Wang

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yian Zhao , Feng Wang , Qiushan Guo , Chang Liu , Xiangyang Ji , Jian Zhang , Jie Chen

Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational Autoencoders (VAEs), achieving higher compression rates is desirable; yet, the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Yubo Dong , Linchao Zhu

Reducing token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common strategy is to build high-compression image tokenizers with more channels per token. However, when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Xin Cai , Zhiyuan You , Zhoutong Zhang , Tianfan Xue

We introduce LTX-Video, a transformer-based latent diffusion model that adopts a holistic approach to video generation by seamlessly integrating the responsibilities of the Video-VAE and the denoising transformer. Unlike existing methods,…

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of…

Recent advances in Latent Video Diffusion Models (LVDMs) have revolutionized video generation by leveraging Video Variational Autoencoders (Video VAEs) to compress intricate video data into a compact latent space. However, as LVDM training…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Yu Cheng , Fajie Yuan

Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compared to continuous video representation. Previous discrete…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Yupeng Zhou , Zhen Li , Ziheng Ouyang , Yuming Chen , Ruoyi Du , Daquan Zhou , Bin Fu , Yihao Liu , Peng Gao , Ming-Ming Cheng , Qibin Hou

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

Machine Learning · Computer Science 2025-08-05 Theodoros Kouzelis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Sen Ye , Jianning Pei , Mengde Xu , Shuyang Gu , Chunyu Wang , Liwei Wang , Han Hu

Latent diffusion models pair VAEs with diffusion backbones, and the structure of VAE latents strongly influences the difficulty of diffusion training. However, existing video VAEs typically focus on reconstruction fidelity, overlooking…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Shizhan Liu , Xinran Deng , Zhuoyi Yang , Jiayan Teng , Xiaotao Gu , Jie Tang

Recent breakthroughs in video autoencoders (Video AEs) have advanced video generation, but existing methods fail to efficiently model spatio-temporal redundancies in dynamics, resulting in suboptimal compression factors. This shortfall…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Huaize Liu , Wenzhang Sun , Qiyuan Zhang , Donglin Di , Biao Gong , Hao Li , Chen Wei , Changqing Zou

Video autoencoders compress videos into compact latent representations for efficient reconstruction, playing a vital role in enhancing the quality and efficiency of video generation. However, existing video autoencoders often entangle…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Cuifeng Shen , Lumin Xu , Xingguo Zhu , Gengdai Liu

Current state-of-the-art generative approaches frequently rely on a two-stage training procedure, where an autoencoder (often a VAE) first performs dimensionality reduction, followed by training a generative model on the learned latent…

Machine Learning · Statistics 2025-07-15 Gianluigi Silvestri , Luca Ambrogioni

The spatio-temporal complexity of video data presents significant challenges in tasks such as compression, generation, and inpainting. We present four key contributions to address the challenges of spatiotemporal video processing. First, we…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Onkar Susladkar , Jishu Sen Gupta , Chirag Sehgal , Sparsh Mittal , Rekha Singhal

Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Jiarui Guan , Wenshuai Zhao , Zhengtao Zou , Juho Kannala , Arno Solin

Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model training costs. However, as the resolution and duration of…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Zongjian Li , Bin Lin , Yang Ye , Liuhan Chen , Xinhua Cheng , Shenghai Yuan , Li Yuan
‹ Prev 1 2 3 10 Next ›