中文
相关论文

相关论文: Towards A Better Metric for Text-to-Video Generati…

200 篇论文

While text-to-video (T2V) generation has achieved remarkable progress in photorealism, generating intent-aligned videos that faithfully obey physics principles remains a core challenge. In this work, we systematically study Newtonian…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Xiangyu Bai , He Liang , Bishoy Galoaa , Utsav Nandi , Shayda Moezzi , Yuhang He , Sarah Ostadabbas

Comprehensive and constructive evaluation protocols play an important role in the development of sophisticated text-to-video (T2V) generation models. Existing evaluation protocols primarily focus on temporal consistency and content…

计算机视觉与模式识别 · 计算机科学 2024-07-02 Mingxiang Liao , Hannan Lu , Xinyu Zhang , Fang Wan , Tianyu Wang , Yuzhong Zhao , Wangmeng Zuo , Qixiang Ye , Jingdong Wang

While Text-To-Video (T2V) models have advanced rapidly, they continue to struggle with generating legible and coherent text within videos. In particular, existing models often fail to render correctly even short phrases or words and…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Ziyang Liu , Kevin Valencia , Justin Cui

Evaluating text-to-vision content hinges on two crucial aspects: visual quality and alignment. While significant progress has been made in developing objective models to assess these dimensions, the performance of such models heavily relies…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Zicheng Zhang , Tengchuan Kou , Shushi Wang , Chunyi Li , Wei Sun , Wei Wang , Xiaoyu Li , Zongyu Wang , Xuezhi Cao , Xiongkuo Min , Xiaohong Liu , Guangtao Zhai

A commonly used evaluation metric for text-to-image synthesis is the Inception score (IS) \cite{inceptionscore}, which has been shown to be a quality metric that correlates well with human judgment. However, IS does not reveal properties of…

机器学习 · 计算机科学 2019-11-04 William Lund Sommer , Alexandros Iosifidis

Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the infrastructure for S2V generation, we propose OpenS2V-Nexus,…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Shenghai Yuan , Xianyi He , Yufan Deng , Yang Ye , Jinfa Huang , Bin Lin , Jiebo Luo , Li Yuan

Recent advancements in large multimodal models (LMMs) have driven substantial progress in both text-to-video (T2V) generation and video-to-text (V2T) interpretation tasks. However, current AI-generated videos (AIGVs) still exhibit…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Jiarui Wang , Huiyu Duan , Ziheng Jia , Yu Zhao , Woo Yi Yang , Zicheng Zhang , Zijian Chen , Juntong Wang , Yuke Xing , Guangtao Zhai , Xiongkuo Min

The rapid advancement of large multimodal models (LMMs) has led to the rapid expansion of artificial intelligence generated videos (AIGVs), which highlights the pressing need for effective video quality assessment (VQA) models designed…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Jiarui Wang , Huiyu Duan , Guangtao Zhai , Juntong Wang , Xiongkuo Min

Generative diffusion models are developing rapidly and attracting increasing attention due to their wide range of applications. Image-to-Video (I2V) generation has become a major focus in the field of video synthesis. However, existing…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Ailing Zhang , Lina Lei , Dehong Kong , Zhixin Wang , Jiaqi Xu , Fenglong Song , Chun-Le Guo , Chang Liu , Fan Li , Jie Chen

While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Zillur Rahman , Alex Sheng , Cristian Meo

The quality of video-text pairs fundamentally determines the upper bound of text-to-video models. Currently, the datasets used for training these models suffer from significant shortcomings, including low temporal consistency, poor-quality…

计算机视觉与模式识别 · 计算机科学 2024-08-06 Zhiyu Tan , Xiaomeng Yang , Luozheng Qin , Hao Li

Recent advances in Large Multimodal Models (LMMs) have expanded their capabilities to video understanding, with Text-to-Video (T2V) models excelling in generating videos from textual prompts. However, they still frequently produce…

Current text-to-video (T2V) generation models are increasingly popular due to their ability to produce coherent videos from textual prompts. However, these models often struggle to generate semantically and temporally consistent videos when…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Minkyu Choi , S P Sharan , Harsh Goel , Sahil Shah , Sandeep Chinchali

The text-to-video (T2V) generation models, offering convenient visual creation, have recently garnered increasing attention. Despite their substantial potential, the generated videos may present artifacts, including structural…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Jiazi Bu , Pengyang Ling , Pan Zhang , Tong Wu , Xiaoyi Dong , Yuhang Zang , Yuhang Cao , Dahua Lin , Jiaqi Wang

The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator,…

计算机视觉与模式识别 · 计算机科学 2024-01-10 Weimin Wang , Jiawei Liu , Zhijie Lin , Jiangqiao Yan , Shuo Chen , Chetwin Low , Tuyen Hoang , Jie Wu , Jun Hao Liew , Hanshu Yan , Daquan Zhou , Jiashi Feng

Recent advancements in image-to-video (I2V) generation have shown promising performance in conventional scenarios. However, these methods still encounter significant challenges when dealing with complex scenes that require a deep…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Peng Liu , Xiaoming Ren , Fengkai Liu , Qingsong Xie , Quanlong Zheng , Yanhao Zhang , Haonan Lu , Yujiu Yang

The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Yuhang Yang , Ke Fan , Shangkun Sun , Hongxiang Li , Ailing Zeng , FeiLin Han , Wei Zhai , Wei Liu , Yang Cao , Zheng-Jun Zha

The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic…

We introduce an approach to generating videos based on a series of given language descriptions. Frames of the video are generated sequentially and optimized by guidance from the CLIP image-text encoder; iterating through language…

计算机视觉与模式识别 · 计算机科学 2022-10-25 Peter Schaldenbrand , Zhixuan Liu , Jean Oh

Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing is on the rise. Building on text-to-image models like Stable…