中文
相关论文

相关论文: Sora Generates Videos with Stunning Geometrical Co…

200 篇论文

OpenAI's Sora highlights the potential of video generation for developing world models that adhere to fundamental physical laws. However, the ability of video generation models to discover such laws purely from visual data without human…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Bingyi Kang , Yang Yue , Rui Lu , Zhijie Lin , Yang Zhao , Kaixin Wang , Gao Huang , Jiashi Feng

Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is trained to generate videos of realistic or imaginative scenes from text instructions and show potential in simulating the physical world. Based…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Yixin Liu , Kai Zhang , Yuan Li , Zhiling Yan , Chujie Gao , Ruoxi Chen , Zhengqing Yuan , Yue Huang , Hanchi Sun , Jianfeng Gao , Lifang He , Lichao Sun

The evolution of video generation from text, from animating MNIST to simulating the world with Sora, has progressed at a breakneck speed. Here, we systematically discuss how far text-to-video generation technology supports essential…

Reconstructing dynamic 3D scenes (i.e., 4D geometry) from monocular video is an important yet challenging problem. Conventional multiview geometry-based approaches often struggle with dynamic motion, whereas recent learning-based methods…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Jinjie Mai , Wenxuan Zhu , Haozhe Liu , Bing Li , Cheng Zheng , Jürgen Schmidhuber , Bernard Ghanem

Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling…

Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Jan Ackermann , Shengqu Cai , Boyang Deng , Zhengfei Kuang , Songyou Peng , Gordon Wetzstein

High-quality video generation, encompassing text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation, holds considerable significance in content creation to benefit anyone express their inherent creativity in new ways…

计算机视觉与模式识别 · 计算机科学 2024-10-11 Ailing Zeng , Yuhang Yang , Weidong Chen , Wei Liu

Emergent capabilities of image generators have led to many impactful zero- or few-shot applications. Inspired by this success, we investigate whether video generators similarly exhibit 3D-awareness. Using structure-from-motion as a 3D-aware…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Chun-Hao Paul Huang , Niloy Mitra , Hyeonho Jeong , Jae Shin Yoon , Duygu Ceylan

Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes,…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Zeyi Liu , Shuang Li , Eric Cousineau , Siyuan Feng , Benjamin Burchfiel , Shuran Song

General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems. Recently, the…

Recent generative models can produce high-fidelity videos, yet they often exhibit 3D spatial geometric inconsistencies. Existing evaluation methods fail to accurately characterize these inconsistencies: fidelity-centric metrics like FVD are…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Weijia Dou , Wenzhao Zheng , Weiliang Chen , Yu Zheng , Jie Zhou , Jiwen Lu

We present a novel method for generating geometrically realistic and consistent orbital videos from a single image of an object. Existing video generation works mostly rely on pixel-wise attention to enforce view consistency across frames.…

计算机视觉与模式识别 · 计算机科学 2026-04-15 Rong Wang , Ruyi Zha , Ziang Cheng , Jiayu Yang , Pulak Purkait , Hongdong Li

We investigate how to enhance the physical fidelity of video generation models by leveraging synthetic videos derived from computer graphics pipelines. These rendered videos respect real-world physics, such as maintaining 3D consistency,…

图像与视频处理 · 电气工程与系统科学 2025-03-28 Qi Zhao , Xingyu Ni , Ziyu Wang , Feng Cheng , Ziyan Yang , Lu Jiang , Bohan Wang

Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Haoyu Wang , Hao Tang , Donglin Di , Zhilu Zhang , Wangmeng Zuo , Feng Gao , Siwei Ma , Shiliang Zhang

Recent advancements in video diffusion models enable the generation of photorealistic videos with impressive 3D consistency and temporal coherence. However, the extent to which these AI-generated videos simulate the 3D visual world remains…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Chirui Chang , Jiahui Liu , Zhengzhe Liu , Xiaoyang Lyu , Yi-Hua Huang , Xin Tao , Pengfei Wan , Di Zhang , Xiaojuan Qi

Sora's high-motion intensity and long consistent videos have significantly impacted the field of video generation, attracting unprecedented attention. However, existing publicly available datasets are inadequate for generating Sora-like…

计算机视觉与模式识别 · 计算机科学 2024-07-10 Xuan Ju , Yiming Gao , Zhaoyang Zhang , Ziyang Yuan , Xintao Wang , Ailing Zeng , Yu Xiong , Qiang Xu , Ying Shan

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

Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned…

计算机视觉与模式识别 · 计算机科学 2026-05-06 Haoyu Wu , Diankun Wu , Tianyu He , Junliang Guo , Yang Ye , Yueqi Duan , Jiang Bian

While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Hongyang Du , Junjie Ye , Xiaoyan Cong , Runhao Li , Jingcheng Ni , Aman Agarwal , Zeqi Zhou , Zekun Li , Randall Balestriero , Yue Wang

Recent advances in video generation have enabled the synthesis of high-quality and visually realistic clips using diffusion transformer models. However, most existing approaches operate purely in the 2D pixel space and lack explicit…

计算机视觉与模式识别 · 计算机科学 2025-12-04 Yunpeng Bai , Shaoheng Fang , Chaohui Yu , Fan Wang , Qixing Huang
‹ 上一页 1 2 3 10 下一页 ›