English
Related papers

Related papers: Improved TokenPose with Sparsity

200 papers

The main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Jinnan Chen , Chen Li , Gim Hee Lee

Multi-person pose estimation in images and videos is an important yet challenging task with many applications. Despite the large improvements in human pose estimation enabled by the development of convolutional neural networks, there still…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Mihai Fieraru , Anna Khoreva , Leonid Pishchulin , Bernt Schiele

Human pose estimation in complicated situations has always been a challenging task. Many Transformer-based pose networks have been proposed recently, achieving encouraging progress in improving performance. However, the remarkable…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Chengpeng Wu , Guangxing Tan , Chunyu Li

In the rapidly evolving field of computer vision, the task of accurately estimating the poses of multiple individuals from various viewpoints presents a formidable challenge, especially if the estimations should be reliable as well. This…

Computer Vision and Pattern Recognition · Computer Science 2024-12-23 Daniel Bermuth , Alexander Poeppel , Wolfgang Reif

Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Wenhao Li , Mengyuan Liu , Hong Liu , Pichao Wang , Jialun Cai , Nicu Sebe

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Ziteng Gao , Zhan Tong , Limin Wang , Mike Zheng Shou

This paper presents Volumetric Transformer Pose estimator (VTP), the first 3D volumetric transformer framework for multi-view multi-person 3D human pose estimation. VTP aggregates features from 2D keypoints in all camera views and directly…

Computer Vision and Pattern Recognition · Computer Science 2023-08-07 Yuxing Chen , Renshu Gu , Ouhan Huang , Gangyong Jia

Humans naturally integrate vision and haptics for robust object perception during manipulation. The loss of either modality significantly degrades performance. Inspired by this multisensory integration, prior object pose estimation research…

Robotics · Computer Science 2025-09-12 Hongyu Li , Mingxi Jia , Tuluhan Akbulut , Yu Xiang , George Konidaris , Srinath Sridhar

For certain manipulation tasks, object pose estimation from head-mounted cameras may not be sufficiently accurate. This is at least in part due to our inability to perfectly calibrate the coordinate frames of today's high degree of freedom…

Robotics · Computer Science 2022-04-12 Patrick Lancaster , Boling Yang , Joshua R. Smith

Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot model the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Zhongwei Qiu , Qiansheng Yang , Jian Wang , Dongmei Fu

We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images). This task is a vital pre-processing stage for nearly all contemporary (neural) reconstruction algorithms but remains challenging given sparse views,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Amy Lin , Jason Y. Zhang , Deva Ramanan , Shubham Tulsiani

Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Martine Hjelkrem-Tan , Marius Aasan , Gabriel Y. Arteaga , Adín Ramírez Rivera

Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervision on large-scale…

Computer Vision and Pattern Recognition · Computer Science 2020-06-26 Jogendra Nath Kundu , Siddharth Seth , Rahul M , Mugalodi Rakesh , R. Venkatesh Babu , Anirban Chakraborty

Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary. But which ones? We evaluate the impact of sparsification…

Computation and Language · Computer Science 2022-10-11 Siddhartha Brahma , Polina Zablotskaia , David Mimno

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Ling Li , David Thorsley , Joseph Hassoun

Recently, human pose estimation mainly focuses on how to design a more effective and better deep network structure as human features extractor, and most designed feature extraction networks only introduce the position of each anatomical…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Zhangjian Ji , Zilong Wang , Ming Zhang , Yapeng Chen , Yuhua Qian

Pose estimation commonly refers to computer vision methods that recognize people's body postures in images or videos. With recent advancements in deep learning, we now have compelling models to tackle the problem in real-time. Since these…

Robotics · Computer Science 2021-07-07 Arash Amini , Hafez Farazi , Sven Behnke

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture…

Computer Vision and Pattern Recognition · Computer Science 2018-12-12 Xiu Li , Yebin Liu , Hanbyul Joo , Qionghai Dai , Yaser Sheikh

To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augmentation techniques are limited to the "seen" pose combinations…

Computer Vision and Pattern Recognition · Computer Science 2023-01-10 Cheng-Yen Yang , Jiajia Luo , Lu Xia , Yuyin Sun , Nan Qiao , Ke Zhang , Zhongyu Jiang , Jenq-Neng Hwang

Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D regions. Existing sparsity methods, designed mainly for 2D…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Sandro Papais , Lezhou Feng , Charles Cossette , Lingting Ge