English
Related papers

Related papers: Fast Encoder-Based 3D from Casual Videos via Point…

200 papers

Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tracking and semantic occupancy prediction lack either spatial…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Zhuoguang Chen , Kenan Li , Xiuyu Yang , Tao Jiang , Yiming Li , Hang Zhao

Most tracking-by-detection methods employ a local search window around the predicted object location in the current frame assuming the previous location is accurate, the trajectory is smooth, and the computational capacity permits a search…

Computer Vision and Pattern Recognition · Computer Science 2015-12-01 Gao Zhu , Fatih Porikli , Hongdong Li

In this paper, we present a simple yet fast and robust algorithm which exploits the spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its local context…

Computer Vision and Pattern Recognition · Computer Science 2013-11-11 Kaihua Zhang , Lei Zhang , Ming-Hsuan Yang , David Zhang

Event sensors offer high temporal resolution visual sensing, which makes them ideal for perceiving fast visual phenomena without suffering from motion blur. Certain applications in robotics and vision-based navigation require 3D perception…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Ethan Elms , Yasir Latif , Tae Ha Park , Tat-Jun Chin

We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the…

Computer Vision and Pattern Recognition · Computer Science 2018-06-04 Wenhan Luo , Peng Sun , Fangwei Zhong , Wei Liu , Tong Zhang , Yizhou Wang

Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs…

Computer Vision and Pattern Recognition · Computer Science 2018-03-08 Christoph Feichtenhofer , Axel Pinz , Andrew Zisserman

3D single object tracking plays an essential role in many applications, such as autonomous driving. It remains a challenging problem due to the large appearance variation and the sparsity of points caused by occlusion and limited sensor…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Tian-Xing Xu , Yuan-Chen Guo , Yu-Kun Lai , Song-Hai Zhang

Recent large multimodal models (LMMs) have become increasingly capable on image and video understanding, yet still struggle to sustain 4D continuous spatiotemporal dynamic reasoning. To study this capability gap, we formulate…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Chaoyue Li , Yongxue Xu , Jie Feng , Jiayu Ding

Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Dong Zhuo , Wenzhao Zheng , Jiahe Guo , Yuqi Wu , Jie Zhou , Jiwen Lu

We introduce CoTracker, a transformer-based model that tracks a large number of 2D points in long video sequences. Differently from most existing approaches that track points independently, CoTracker tracks them jointly, accounting for…

Computer Vision and Pattern Recognition · Computer Science 2024-10-02 Nikita Karaev , Ignacio Rocco , Benjamin Graham , Natalia Neverova , Andrea Vedaldi , Christian Rupprecht

Estimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Zhuoyuan Wu , Xurui Yang , Jiahui Huang , Yue Wang , Jun Gao

We present PAD3R, a method for reconstructing deformable 3D objects from casually captured, unposed monocular videos. Unlike existing approaches, PAD3R handles long video sequences featuring substantial object deformation, large-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Ting-Hsuan Liao , Haowen Liu , Yiran Xu , Songwei Ge , Gengshan Yang , Jia-Bin Huang

3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also computationally inefficient due to the processing of point…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Fan Yang , Feiran Li , Yang Wu , Sakriani Sakti , Satoshi Nakamura

Recent advances in transformer-based lightweight object tracking have established new standards across benchmarks, leveraging the global receptive field and powerful feature extraction capabilities of attention mechanisms. Despite these…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Junze Shi , Yang Yu , Jian Shi , Haibo Luo

In this thesis, we propose a pioneering work on sparse keypoints tracking across images using transformer networks. While deep learning-based keypoints matching have been widely investigated using graph neural networks - and more recently…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Oleksii Nasypanyi , Francois Rameau

Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature.…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Gengshan Yang , Deqing Sun , Varun Jampani , Daniel Vlasic , Forrester Cole , Huiwen Chang , Deva Ramanan , William T. Freeman , Ce Liu

We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely on local 2D correlation maps to establish correspondences…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Seokju Cho , Jiahui Huang , Jisu Nam , Honggyu An , Seungryong Kim , Joon-Young Lee

Understanding dynamic scenes from casual videos is critical for scalable robot learning, yet four-dimensional (4D) reconstruction under strictly monocular settings remains highly ill-posed. To address this challenge, our key insight is that…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Can Li , Jie Gu , Jingmin Chen , Fangzhou Qiu , Lei Sun

We present a novel approach for hand-object action recognition that leverages 2D point tracks as an additional motion cue. While most existing methods rely on RGB appearance, human pose estimation, or their combination, our work…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Dennis Holzmann , Sven Wachsmuth

The availability of large-scale multimodal datasets and advancements in diffusion models have significantly accelerated progress in 4D content generation. Most prior approaches rely on multiple image or video diffusion models, utilizing…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Hanwen Liang , Yuyang Yin , Dejia Xu , Hanxue Liang , Zhangyang Wang , Konstantinos N. Plataniotis , Yao Zhao , Yunchao Wei
‹ Prev 1 4 5 6 7 8 10 Next ›