中文
相关论文

相关论文: STAR: Spatial-Temporal Augmentation with Text-to-V…

200 篇论文

Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Aniruddha Mahapatra , Long Mai , David Bourgin , Yitian Zhang , Feng Liu

Visual Autoregressive modeling (VAR) has emerged as a highly efficient alternative to diffusion-based frameworks, achieving comparable synthesis quality. However, as this paradigm extends to Spacetime Autoregressive modeling (STAR) for…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Sungwoong Yune , Suheon Jeong , Joo-Young Kim

Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual…

Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safety challenges. Existing safety evaluation methods,which focus…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Jiaming He , Guanyu Hou , Hongwei Li , Zhicong Huang , Kangjie Chen , Yi Yu , Wenbo Jiang , Guowen Xu , Tianwei Zhang

Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Ce Wang , Zhenyu Hu , Wanjie Sun , Zhenzhong Chen

Text-to-video diffusion models have advanced video generation significantly. However, customizing these models to generate videos with tailored motions presents a substantial challenge. In specific, they encounter hurdles in (a) accurately…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Hyeonho Jeong , Geon Yeong Park , Jong Chul Ye

We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space…

计算机视觉与模式识别 · 计算机科学 2023-04-19 Jie An , Songyang Zhang , Harry Yang , Sonal Gupta , Jia-Bin Huang , Jiebo Luo , Xi Yin

The target of space-time video super-resolution (STVSR) is to increase both the frame rate (also referred to as the temporal resolution) and the spatial resolution of a given video. Recent approaches solve STVSR using end-to-end deep neural…

计算机视觉与模式识别 · 计算机科学 2024-12-25 Zijie Yue , Miaojing Shi

We present a novel image editing scenario termed Text-grounded Object Generation (TOG), defined as generating a new object in the real image spatially conditioned by textual descriptions. Existing diffusion models exhibit limitations of…

计算机视觉与模式识别 · 计算机科学 2024-03-18 Xiangtian Xue , Jiasong Wu , Youyong Kong , Lotfi Senhadji , Huazhong Shu

Recent advances in text-to-video (T2V) diffusion models have significantly enhanced the quality of generated videos. However, their capability to produce explicit or harmful content introduces new challenges related to misuse and potential…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Xiaoyu Ye , Songjie Cheng , Yongtao Wang , Yajiao Xiong , Yishen Li

Video diffusion models have recently shown promise for world modeling through autoregressive frame prediction conditioned on actions. However, they struggle to maintain long-term memory due to the high computational cost associated with…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Ryan Po , Yotam Nitzan , Richard Zhang , Berlin Chen , Tri Dao , Eli Shechtman , Gordon Wetzstein , Xun Huang

Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by…

计算机视觉与模式识别 · 计算机科学 2023-12-20 Xirui Li , Chao Ma , Xiaokang Yang , Ming-Hsuan Yang

Text-to-video (T2V) diffusion models have shown promising capabilities in synthesizing realistic videos from input text prompts. However, the input text description alone provides limited control over the precise objects movements and…

计算机视觉与模式识别 · 计算机科学 2025-02-20 Yen-Siang Wu , Chi-Pin Huang , Fu-En Yang , Yu-Chiang Frank Wang

Recent advances in Text-to-Video generation (T2V) have achieved remarkable success in synthesizing high-quality general videos from textual descriptions. A largely overlooked problem in T2V is that existing models have not adequately…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Shenghai Yuan , Jinfa Huang , Yujun Shi , Yongqi Xu , Ruijie Zhu , Bin Lin , Xinhua Cheng , Li Yuan , Jiebo Luo

Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Shangjin Zhai , Zhichao Ye , Jialin Liu , Weijian Xie , Jiaqi Hu , Zhen Peng , Hua Xue , Danpeng Chen , Xiaomeng Wang , Lei Yang , Nan Wang , Haomin Liu , Guofeng Zhang

We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Junyang Chen , Jiangxin Dong , Long Sun , Yixin Yang , Jinshan Pan

Real-world text image super-resolution aims to restore overall visual quality and text legibility in images suffering from diverse degradations and text distortions. However, the scarcity of text image data in existing datasets results in…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Haodong He , Xin Zhan , Yancheng Bai , Rui Lan , Lei Sun , Xiangxiang Chu

Although recent research applying text-to-image (T2I) diffusion models to real-world super-resolution (SR) has achieved remarkable progress, the misalignment of their targets leads to a suboptimal trade-off between inference speed and…

计算机视觉与模式识别 · 计算机科学 2026-02-12 Yan Wang , Shijie Zhao , Kexin Zhang , Junlin Li , Li Zhang

Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous…

计算机视觉与模式识别 · 计算机科学 2024-07-12 Zhening Xing , Gereon Fox , Yanhong Zeng , Xingang Pan , Mohamed Elgharib , Christian Theobalt , Kai Chen

Optical-flow-based and kernel-based approaches have been extensively explored for temporal compensation in satellite Video Super-Resolution (VSR). However, these techniques are less generalized in large-scale or complex scenarios,…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Yi Xiao , Qiangqiang Yuan , Kui Jiang , Xianyu Jin , Jiang He , Liangpei Zhang , Chia-Wen Lin