中文
相关论文

相关论文: MAGI-1: Autoregressive Video Generation at Scale

200 篇论文

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method…

计算机视觉与模式识别 · 计算机科学 2023-04-06 Lijun Yu , Yong Cheng , Kihyuk Sohn , José Lezama , Han Zhang , Huiwen Chang , Alexander G. Hauptmann , Ming-Hsuan Yang , Yuan Hao , Irfan Essa , Lu Jiang

An image may convey a thousand words, but a video composed of hundreds or thousands of image frames tells a more intricate story. Despite significant progress in multimodal large language models (MLLMs), generating extended videos remains a…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Faraz Waseem , Muhammad Shahzad

We propose a novel text-to-video (T2V) generation benchmark, ChronoMagic-Bench, to evaluate the temporal and metamorphic capabilities of the T2V models (e.g. Sora and Lumiere) in time-lapse video generation. In contrast to existing…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Shenghai Yuan , Jinfa Huang , Yongqi Xu , Yaoyang Liu , Shaofeng Zhang , Yujun Shi , Ruijie Zhu , Xinhua Cheng , Jiebo Luo , Li Yuan

Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Taiye Chen , Xun Hu , Zihan Ding , Chi Jin

We present an efficient framework that can generate a coherent paragraph to describe a given video. Previous works on video captioning usually focus on video clips. They typically treat an entire video as a whole and generate the caption…

计算机视觉与模式识别 · 计算机科学 2018-07-27 Yilei Xiong , Bo Dai , Dahua Lin

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text…

计算机视觉与模式识别 · 计算机科学 2025-08-18 Jiasong Feng , Ao Ma , Jing Wang , Ke Cao , Zhanjie Zhang

Human video generation task has gained significant attention with the advancement of deep generative models. Generating realistic videos with human movements is challenging in nature, due to the intricacies of human body topology and…

计算机视觉与模式识别 · 计算机科学 2024-09-04 Zhangsihao Yang , Mengyi Shan , Mohammad Farazi , Wenhui Zhu , Yanxi Chen , Xuanzhao Dong , Yalin Wang

Diffusion transformers enable flexible generative modeling for video. However, it is still technically challenging and computationally expensive to generate high-resolution videos with rich semantics and complex motion. Similar to…

计算机视觉与模式识别 · 计算机科学 2024-12-16 Xunnong Xu , Mengying Cao

Recent advances in the diffusion models have significantly improved text-to-image generation. However, generating videos from text is a more challenging task than generating images from text, due to the much larger dataset and higher…

计算机视觉与模式识别 · 计算机科学 2024-12-31 Taegyeong Lee , Soyeong Kwon , Taehwan Kim

GANs are able to perform generation and manipulation tasks, trained on a single video. However, these single video GANs require unreasonable amount of time to train on a single video, rendering them almost impractical. In this paper we…

计算机视觉与模式识别 · 计算机科学 2022-05-13 Niv Haim , Ben Feinstein , Niv Granot , Assaf Shocher , Shai Bagon , Tali Dekel , Michal Irani

Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Kesen Zhao , Jiaxin Shi , Beier Zhu , Junbao Zhou , Xiaolong Shen , Yuan Zhou , Qianru Sun , Hanwang Zhang

The rapid increase in video content production has resulted in enormous data volumes, creating significant challenges for efficient analysis and resource management. To address this, robust video analysis tools are essential. This paper…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Ulindu De Silva , Leon Fernando , Billy Lau Pik Lik , Zann Koh , Sam Conrad Joyce , Belinda Yuen , Chau Yuen

Creation of images using generative adversarial networks has been widely adapted into multi-modal regime with the advent of multi-modal representation models pre-trained on large corpus. Various modalities sharing a common representation…

声音 · 计算机科学 2022-06-10 Yoonjeon Kim , Joel Jang , Sumin Shin

GANs are able to perform generation and manipulation tasks, trained on a single video. However, these single video GANs require unreasonable amount of time to train on a single video, rendering them almost impractical. In this paper we…

计算机视觉与模式识别 · 计算机科学 2021-12-07 Niv Haim , Ben Feinstein , Niv Granot , Assaf Shocher , Shai Bagon , Tali Dekel , Michal Irani

Recent successful video generation systems that predict and create realistic automotive driving scenes from short video inputs assign tokenization, future state prediction (world model), and video decoding to dedicated models. These…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Björn Möller , Zhengyang Li , Malte Stelzer , Thomas Graave , Fabian Bettels , Muaaz Ataya , Tim Fingscheidt

Music enhances video narratives and emotions, driving demand for automatic video-to-music (V2M) generation. However, existing V2M methods relying solely on visual features or supplementary textual inputs generate music in a black-box…

多媒体 · 计算机科学 2025-07-29 Junxian Wu , Weitao You , Heda Zuo , Dengming Zhang , Pei Chen , Lingyun Sun

In recent years, generative artificial intelligence has achieved significant advancements in the field of image generation, spawning a variety of applications. However, video generation still faces considerable challenges in various…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Yuang Zhang , Jiaxi Gu , Li-Wen Wang , Han Wang , Junqi Cheng , Yuefeng Zhu , Fangyuan Zou

We introduce MG-Gen, a framework that generates motion graphics directly from a single raster image. MG-Gen decompose a single raster image into layered structures represented as HTML, generate animation scripts for each layer, and then…

图形学 · 计算机科学 2025-07-15 Takahiro Shirakawa , Tomoyuki Suzuki , Takuto Narumoto , Daichi Haraguchi

We present GLASS, a method for Global and Local Action-driven Sequence Synthesis. GLASS is a generative model that is trained on video sequences in an unsupervised manner and that can animate an input image at test time. The method learns…

计算机视觉与模式识别 · 计算机科学 2022-04-14 Aram Davtyan , Paolo Favaro

World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Jialong Wu , Shaofeng Yin , Ningya Feng , Xu He , Dong Li , Jianye Hao , Mingsheng Long