中文
相关论文

相关论文: GeoMag: Geometric-Aware Video Motion Magnification…

200 篇论文

Multi-view image generation holds significant application value in computer vision, particularly in domains like 3D reconstruction, virtual reality, and augmented reality. Most existing methods, which rely on extending single images, face…

计算机视觉与模式识别 · 计算机科学 2025-11-20 Jiaqi Wu , Yaosen Chen , Shuyuan Zhu

Despite tremendous recent progress, generative video models still struggle to capture real-world motion, dynamics, and physics. We show that this limitation arises from the conventional pixel reconstruction objective, which biases models…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Hila Chefer , Uriel Singer , Amit Zohar , Yuval Kirstain , Adam Polyak , Yaniv Taigman , Lior Wolf , Shelly Sheynin

Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. However, state-of-the-art video diffusion models frequently produce implausible results such as…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Siwei Meng , Yawei Luo , Ping Liu

Despite their proficiency in general tasks, Multi-modal Large Language Models (MLLMs) struggle with automatic Geometry Problem Solving (GPS), which demands understanding diagrams, interpreting symbols, and performing complex reasoning. This…

计算机视觉与模式识别 · 计算机科学 2025-01-13 Renqiu Xia , Mingsheng Li , Hancheng Ye , Wenjie Wu , Hongbin Zhou , Jiakang Yuan , Tianshuo Peng , Xinyu Cai , Xiangchao Yan , Bin Wang , Conghui He , Botian Shi , Tao Chen , Junchi Yan , Bo Zhang

Video object segmentation methods like SAM2 achieve strong performance through memory-based architectures but struggle under large viewpoint changes due to reliance on appearance features. Traditional 3D instance segmentation methods…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Yang-Che Sun , Cheng Sun , Chin-Yang Lin , Fu-En Yang , Min-Hung Chen , Yen-Yu Lin , Yu-Lun Liu

We present PanoWorld, a panoramic video world model that generates geometry-consistent 360$\degree$ video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do not explicitly…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Le Jiang , Xiangyu Bai , Bishoy Galoaa , Shayda Moezzi , Caleb James Lee , Tooba Imtiaz , Edmund Yeh , Jennifer Dy , Yanzhi Wang , Sarah Ostadabbas

Structure-from-motion (SfM) is a long-standing problem in the computer vision community, which aims to reconstruct the camera poses and 3D structure of a scene from a set of unconstrained 2D images. Classical frameworks solve this problem…

计算机视觉与模式识别 · 计算机科学 2023-12-08 Jianyuan Wang , Nikita Karaev , Christian Rupprecht , David Novotny

Reconstructing dynamic 3D scenes from blurry monocular videos is challenging as motion-induced blur entangles object motion and geometry, hindering geometric consistency. We present Kinematics-GS, a kinematics-aware framework that models…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Yeon-Ji Song , Kiyoung Kwon , Junoh Lee , Jin-Hwa Kim , Byoung-Tak Zhang

Vision transformers have recently emerged as an effective alternative to convolutional networks for action recognition. However, vision transformers still struggle with geometric variations prevalent in video data. This paper proposes a…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Jinhui Ye , Jiaming Zhou , Hui Xiong , Junwei Liang

Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have made remarkable progress with the use of large-scale transformers. Their prohibitive computational and memory costs severely hinder…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Weilun Feng , Haotong Qin , Mingqiang Wu , Chuanguang Yang , Yuqi Li , Xiangqi Li , Zhulin An , Libo Huang , Yulun Zhang , Michele Magno , Yongjun Xu

Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between. One cause of this failure arises before language reasoning begins: the…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Renjie Gu , Kaichen Zhou , Yan Luo , Mengyu Wang

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

Geometry problem-solving demands advanced reasoning abilities to process multimodal inputs and employ mathematical knowledge effectively. Vision-language models (VLMs) have made significant progress in various multimodal tasks. Yet, they…

计算与语言 · 计算机科学 2024-10-18 Aditya Sharma , Aman Dalmia , Mehran Kazemi , Amal Zouaq , Christopher J. Pal

Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of…

计算机视觉与模式识别 · 计算机科学 2026-01-19 Qiyuan Zhang , Biao Gong , Shuai Tan , Zheng Zhang , Yujun Shen , Xing Zhu , Yuyuan Li , Kelu Yao , Chunhua Shen , Changqing Zou

Streaming Visual Geometry Transformers such as StreamVGGT enable strong online 3D perception, but their KV-cache grows unbounded over long streams, limiting practical deployment. We revisit bounded-memory streaming from the perspective of…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Zhisong Xu , Takeshi Oishi

\textbf{Synthetic human dynamics} aims to generate photorealistic videos of human subjects performing expressive, intention-driven motions. However, current approaches face two core challenges: (1) \emph{geometric inconsistency} and…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Weiqi Li , Zehao Zhang , Liang Lin , Guangrun Wang

Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Yongtao Ge , Kangyang Xie , Guangkai Xu , Mingyu Liu , Li Ke , Longtao Huang , Hui Xue , Hao Chen , Chunhua Shen

Human motion synthesis is an important problem with applications in graphics, gaming and simulation environments for robotics. Existing methods require accurate motion capture data for training, which is costly to obtain. Instead, we…

计算机视觉与模式识别 · 计算机科学 2022-08-15 Kevin Xie , Tingwu Wang , Umar Iqbal , Yunrong Guo , Sanja Fidler , Florian Shkurti

Previous works leveraging video models for image-to-3D scene generation tend to suffer from geometric distortions and blurry content. In this paper, we renovate the pipeline of image-to-3D scene generation by unlocking the potential of…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Yuhao Wan , Lijuan Liu , Jingzhi Zhou , Zihan Zhou , Xuying Zhang , Dongbo Zhang , Shaohui Jiao , Qibin Hou , Ming-Ming Cheng

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…

计算机视觉与模式识别 · 计算机科学 2018-12-04 Hassan Abu Alhaija , Siva Karthik Mustikovela , Andreas Geiger , Carsten Rother