中文
相关论文

相关论文: Snap Video: Scaled Spatiotemporal Transformers for…

200 篇论文

Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification. Three main challenges exist including…

计算机视觉与模式识别 · 计算机科学 2018-07-30 Saining Xie , Chen Sun , Jonathan Huang , Zhuowen Tu , Kevin Murphy

We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models. Given a text prompt, Imagen Video generates high definition videos using a base video generation model and a sequence of…

The ability to visualize a structure from multiple perspectives is crucial for comprehensive planning and presentation. This paper introduces an advanced application of generative models, akin to Stable Video Diffusion, tailored for…

人机交互 · 计算机科学 2024-06-05 Mingming Wang , Elijah Miller

Image-to-video generation, which aims to generate a video starting from a given reference image, has drawn great attention. Existing methods try to extend pre-trained text-guided image diffusion models to image-guided video generation…

计算机视觉与模式识别 · 计算机科学 2024-09-17 Cong Wang , Jiaxi Gu , Panwen Hu , Songcen Xu , Hang Xu , Xiaodan Liang

Downsampling is one of the most basic image processing operations. Improper spatio-temporal downsampling applied on videos can cause aliasing issues such as moir\'e patterns in space and the wagon-wheel effect in time. Consequently, the…

计算机视觉与模式识别 · 计算机科学 2022-03-16 Xiaoyu Xiang , Yapeng Tian , Vijay Rengarajan , Lucas Young , Bo Zhu , Rakesh Ranjan

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

State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can generate high-quality videos, it suffers from slow convergence…

计算机视觉与模式识别 · 计算机科学 2025-12-29 Jianhong Bai , Xiaoshi Wu , Xintao Wang , Xiao Fu , Yuanxing Zhang , Qinghe Wang , Xiaoyu Shi , Menghan Xia , Zuozhu Liu , Haoji Hu , Pengfei Wan , Kun Gai

The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers…

计算机视觉与模式识别 · 计算机科学 2021-06-25 Ze Liu , Jia Ning , Yue Cao , Yixuan Wei , Zheng Zhang , Stephen Lin , Han Hu

Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and editing. This study explores the potential of extending the…

计算机视觉与模式识别 · 计算机科学 2023-05-30 Fu-Yun Wang , Wenshuo Chen , Guanglu Song , Han-Jia Ye , Yu Liu , Hongsheng Li

We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video…

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-image diffusion models in an optimization problem or…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Lukas Höllein , Aljaž Božič , Norman Müller , David Novotny , Hung-Yu Tseng , Christian Richardt , Michael Zollhöfer , Matthias Nießner

Technological advances in sensors have paved the way for digital cameras to become increasingly ubiquitous, which, in turn, led to the popularity of the self-recording culture. As a result, the amount of visual data on the Internet is…

计算机视觉与模式识别 · 计算机科学 2020-09-24 Michel Melo Silva , Washington Luis Souza Ramos , Mario Fernando Montenegro Campos , Erickson Rangel Nascimento

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…

计算机视觉与模式识别 · 计算机科学 2020-01-13 Ximeng Sun , Huijuan Xu , Kate Saenko

The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN…

计算机视觉与模式识别 · 计算机科学 2019-08-23 Ji Lin , Chuang Gan , Song Han

Text-to-Video (T2V) generation has attracted significant attention for its ability to synthesize realistic videos from textual descriptions. However, existing models struggle to balance computational efficiency and high visual quality,…

计算机视觉与模式识别 · 计算机科学 2025-11-03 Takashi Isobe , He Cui , Dong Zhou , Mengmeng Ge , Dong Li , Emad Barsoum

Recent text-to-image generation methods provide a simple yet exciting conversion capability between text and image domains. While these methods have incrementally improved the generated image fidelity and text relevancy, several pivotal…

计算机视觉与模式识别 · 计算机科学 2022-03-25 Oran Gafni , Adam Polyak , Oron Ashual , Shelly Sheynin , Devi Parikh , Yaniv Taigman

Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting their use on mobile devices. This paper introduces the first mobile-optimized video diffusion model.…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Haitam Ben Yahia , Denis Korzhenkov , Ioannis Lelekas , Amir Ghodrati , Amirhossein Habibian

The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with vast potential in AR/VR and world modeling. While panoramic images have proven effective…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Felix Wimbauer , Fabian Manhardt , Michael Oechsle , Nikolai Kalischek , Christian Rupprecht , Daniel Cremers , Federico Tombari

As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery…

计算机视觉与模式识别 · 计算机科学 2023-06-21 Gen Li , Jie Ji , Minghai Qin , Wei Niu , Bin Ren , Fatemeh Afghah , Linke Guo , Xiaolong Ma

Recently, great progress has been achieved in text-to-video (T2V) generation by scaling transformer-based diffusion models to billions of parameters, which can generate high-quality videos. However, existing models typically produce only…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Akio Kodaira , Tingbo Hou , Ji Hou , Markos Georgopoulos , Felix Juefei-Xu , Masayoshi Tomizuka , Yue Zhao