English
Related papers

Related papers: KV-Tracker: Real-Time Pose Tracking with Transform…

200 papers

We present a temporal 6-DOF tracking method which leverages deep learning to achieve state-of-the-art performance on challenging datasets of real world capture. Our method is both more accurate and more robust to occlusions than the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-17 Mathieu Garon , Jean-François Lalonde

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by…

Computer Vision and Pattern Recognition · Computer Science 2020-08-24 Xingyi Zhou , Vladlen Koltun , Philipp Krähenbühl

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Zipeng Wang , Dan Xu

We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance…

Computer Vision and Pattern Recognition · Computer Science 2018-08-28 Ilchae Jung , Jeany Son , Mooyeol Baek , Bohyung Han

Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance. Nonetheless, the Key-Value (KV) cache expands linearly over time, leading to substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Zhenyu Ning , Guangda Liu , Qihao Jin , Chengwei Li , Wenchao Ding , Minyi Guo , Jieru Zhao

High-quality motion reconstruction that follows the user's movements can be achieved by high-end mocap systems with many sensors. However, obtaining such animation quality with fewer input devices is gaining popularity as it brings mocap…

Graphics · Computer Science 2025-06-03 Jose Luis Ponton , Eduard Pujol , Andreas Aristidou , Carlos Andujar , Nuria Pelechano

Sequential Visual Place Recognition (Seq-VPR) leverages transformers to capture spatio-temporal features effectively. In practice, a transformer-based Seq-VPR model should be flexible to the number of frames per sequence (seq- length),…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yu Kiu , Lau , Chao Chen , Ge Jin , Chen Feng

We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network architecture contains two branches: a keypoint branch that…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Lihui Qian , Xintong Han , Faqiang Wang , Hongyu Liu , Haoye Dong , Zhiwen Li , Huawei Wei , Zhe Lin , Cheng-Bin Jin

Acquiring 3D geometry of real world objects has various applications in 3D digitization, such as navigation and content generation in virtual environments. Image remains one of the most popular media for such visual tasks due to its…

Computer Vision and Pattern Recognition · Computer Science 2017-01-26 Shuai Du , Youyi Zheng

It remains a huge challenge to design effective and efficient trackers under complex scenarios, including occlusions, illumination changes and pose variations. To cope with this problem, a promising solution is to integrate the temporal…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Peng Zhang , Shujian Yu , Jiamiao Xu , Xinge You , Xiubao Jiang , Xiao-Yuan Jing , Dacheng Tao

Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Sebastian Lutz , Richard Blythman , Koustav Ghosal , Matthew Moynihan , Ciaran Simms , Aljosa Smolic

In this paper, we present TANDEM a real-time monocular tracking and dense mapping framework. For pose estimation, TANDEM performs photometric bundle adjustment based on a sliding window of keyframes. To increase the robustness, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Lukas Koestler , Nan Yang , Niclas Zeller , Daniel Cremers

We propose a complete pipeline that allows object detection and simultaneously estimate the pose of these multiple object instances using just a single image. A novel "keypoint regression" scheme with a cross-ratio term is introduced that…

Computer Vision and Pattern Recognition · Computer Science 2018-09-28 Ankit Dhall

Tracking and reconstructing the 3D pose and geometry of two hands in interaction is a challenging problem that has a high relevance for several human-computer interaction applications, including AR/VR, robotics, or sign language…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Jiayi Wang , Franziska Mueller , Florian Bernard , Suzanne Sorli , Oleksandr Sotnychenko , Neng Qian , Miguel A. Otaduy , Dan Casas , Christian Theobalt

This paper addresses the problem of reconstructing a scene online at the level of objects given an RGB-D video sequence. While current object-aware neural implicit representations hold promise, they are limited in online reconstruction…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Thomas Chabal , Shizhe Chen , Jean Ponce , Cordelia Schmid

Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images. However, in most cases image-sequences, rather only…

Computer Vision and Pattern Recognition · Computer Science 2017-08-01 Ronald Clark , Sen Wang , Andrew Markham , Niki Trigoni , Hongkai Wen

Semantic aware reconstruction is more advantageous than geometric-only reconstruction for future robotic and AR/VR applications because it represents not only where things are, but also what things are. Object-centric mapping is a task to…

Computer Vision and Pattern Recognition · Computer Science 2021-02-16 Kejie Li , Hamid Rezatofighi , Ian Reid

High-quality, animatable 3D human avatar reconstruction from monocular videos offers significant potential for reducing reliance on complex hardware, making it highly practical for applications in game development, augmented reality, and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Xia Yuan , Hai Yuan , Wenyi Ge , Ying Fu , Xi Wu , Guanyu Xing

Point tracking in video sequences is a foundational capability for real-world computer vision applications, including robotics, autonomous systems, augmented reality, and video analysis. While recent deep learning-based trackers achieve…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Bishoy Galoaa , Pau Closas , Sarah Ostadabbas

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…

Computer Vision and Pattern Recognition · Computer Science 2019-12-05 Ilchae Jung , Kihyun You , Hyeonwoo Noh , Minsu Cho , Bohyung Han