English
Related papers

Related papers: VidTwin: Video VAE with Decoupled Structure and Dy…

200 papers

Given the complex geometry of white matter streamlines, Autoencoders have been proposed as a dimension-reduction tool to simplify the analysis streamlines in a low-dimensional latent spaces. However, despite these recent successes, the…

Machine Learning · Statistics 2023-11-21 Andrew Lizarraga , Brandon Taraku , Edouardo Honig , Ying Nian Wu , Shantanu H. Joshi

The exponential growth of video traffic has placed increasing demands on bandwidth and storage infrastructure, particularly for content delivery networks (CDNs) and edge devices. While traditional video codecs like H.264 and HEVC achieve…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Manikanta Kotthapalli , Banafsheh Rekabdar

Latent diffusion models have enabled high-quality video synthesis, yet their inference remains costly and time-consuming. As diffusion transformers become increasingly efficient, the latency bottleneck inevitably shifts to VAE decoders. To…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Lunjie Zhu , Yushi Huang , Xingtong Ge , Yufei Xue , Zhening Liu , Yumeng Zhang , Zehong Lin , Jun Zhang

In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community. In this paper we propose a novel approach to this problem with Vector Quantized Variational…

Computer Vision and Pattern Recognition · Computer Science 2021-03-03 Jacob Walker , Ali Razavi , Aäron van den Oord

A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in…

Computer Vision and Pattern Recognition · Computer Science 2021-10-07 Zihang Lai , Sifei Liu , Alexei A. Efros , Xiaolong Wang

Video generation powers a vast array of downstream applications. However, while the de facto standard, i.e., latent diffusion models, typically employ heavily conditioned denoising networks, their decoders often remain unconditional. We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Xiang Fan , Yuheng Wang , Bohan Fang , Zhongzheng Ren , Ranjay Krishna

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

We present fast, realistic image generation on high-resolution, multimodal datasets using hierarchical variational autoencoders (VAEs) trained on a deterministic autoencoder's latent space. In this two-stage setup, the autoencoder…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Troy Luhman , Eric Luhman

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Anni Tang , Tianyu He , Junliang Guo , Xinle Cheng , Li Song , Jiang Bian

Constructing powerful generative models for natural images is a challenging task. PixelCNN models capture details and local information in images very well but have limited receptive field. Variational autoencoders with a factorial decoder…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Hossein Sadeghi , Evgeny Andriyash , Walter Vinci , Lorenzo Buffoni , Mohammad H. Amin

We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression,…

Video diffusion models have recently made great progress in generation quality, but are still limited by the high memory and computational requirements. This is because current video diffusion models often attempt to process…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Sihyun Yu , Weili Nie , De-An Huang , Boyi Li , Jinwoo Shin , Anima Anandkumar

Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the…

Image and Video Processing · Electrical Eng. & Systems 2024-09-05 Zhiyuan Li , Yanhui Zhou , Hao Wei , Chenyang Ge , Jingwen Jiang

Self-supervised learning has attracted increasing attention as it learns data-driven representation from data without annotations. Vision transformer-based autoencoder (ViT-AE) by He et al. (2021) is a recent self-supervised learning…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Chinmay Prabhakar , Hongwei Bran Li , Jiancheng Yang , Suprosana Shit , Benedikt Wiestler , Bjoern Menze

Latent variable generative models have emerged as powerful tools for generative tasks including image and video synthesis. These models are enabled by pretrained autoencoders that map high resolution data into a compressed lower dimensional…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Mohammed Suhail , Carlos Esteves , Leonid Sigal , Ameesh Makadia

Autoencoder (AE) is the key to the success of latent diffusion models for image and video generation, reducing the denoising resolution and improving efficiency. However, the power of AE has long been underexplored in terms of network…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Yushu Wu , Yanyu Li , Ivan Skorokhodov , Anil Kag , Willi Menapace , Sharath Girish , Aliaksandr Siarohin , Yanzhi Wang , Sergey Tulyakov

Video generation is an inherently challenging task, as it requires modeling realistic temporal dynamics as well as spatial content. Existing methods entangle the two intrinsically different tasks of motion and content creation in a single…

Computer Vision and Pattern Recognition · Computer Science 2020-01-13 Ximeng Sun , Huijuan Xu , Kate Saenko

This paper introduces a novel approach for generating videos called Synchronized Deep Recurrent Attentive Writer (Sync-DRAW). Sync-DRAW can also perform text-to-video generation which, to the best of our knowledge, makes it the first…

Computer Vision and Pattern Recognition · Computer Science 2017-10-24 Gaurav Mittal , Tanya Marwah , Vineeth N. Balasubramanian

This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Ashkan Taghipour , Morteza Ghahremani , Mohammed Bennamoun , Aref Miri Rekavandi , Zinuo Li , Hamid Laga , Farid Boussaid

We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion model (LDM)…