English
Related papers

Related papers: ViTPose: Simple Vision Transformer Baselines for H…

200 papers

The task of 2D human pose estimation is challenging as the number of keypoints is typically large (~ 17) and this necessitates the use of robust neural network architectures and training pipelines that can capture the relevant features from…

Machine Learning · Computer Science 2022-04-22 Kaushik Balakrishnan , Devesh Upadhyay

6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications. The state-of-the-art models for pose estimation are convolutional neural network (CNN)-based. Lately, Transformers, an architecture…

Computer Vision and Pattern Recognition · Computer Science 2022-05-06 Arash Amini , Arul Selvam Periyasamy , Sven Behnke

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 René Ranftl , Alexey Bochkovskiy , Vladlen Koltun

Transformer is popular in recent 3D human pose estimation, which utilizes long-term modeling to lift 2D keypoints into the 3D space. However, current transformer-based methods do not fully exploit the prior knowledge of the human skeleton…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Yaqi Zhang , Yan Lu , Bin Liu , Zhiwei Zhao , Qi Chu , Nenghai Yu

As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount. Existing methods often resort to post-hoc techniques or prototypes to…

Computer Vision and Pattern Recognition · Computer Science 2024-01-31 Danning Lao , Qi Liu , Jiazi Bu , Junchi Yan , Wei Shen

In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and minimal latency…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Ben Usman , Andrea Tagliasacchi , Kate Saenko , Avneesh Sud

High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Anthony Fuller , Daniel G. Kyrollos , Yousef Yassin , James R. Green

Transformers have become a default architecture in computer vision, but understanding what drives their predictions remains a challenging problem. Current explanation approaches rely on attention values or input gradients, but these provide…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Ian Covert , Chanwoo Kim , Su-In Lee

Multi-person pose estimation generally follows top-down and bottom-up paradigms. Both of them use an extra stage ($\boldsymbol{e.g.,}$ human detection in top-down paradigm or grouping process in bottom-up paradigm) to build the relationship…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Yabo Xiao , Xiaojuan Wang , Dongdong Yu , Kai Su , Lei Jin , Mei Song , Shuicheng Yan , Jian Zhao

Advances in computing have enabled widespread access to pose estimation, creating new sources of data streams. Unlike mock set-ups for data collection, tapping into these data streams through on-device active learning allows us to directly…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Megh Shukla , Roshan Roy , Pankaj Singh , Shuaib Ahmed , Alexandre Alahi

We propose FoundPose, a model-based method for 6D pose estimation of unseen objects from a single RGB image. The method can quickly onboard new objects using their 3D models without requiring any object- or task-specific training. In…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Evin Pınar Örnek , Yann Labbé , Bugra Tekin , Lingni Ma , Cem Keskin , Christian Forster , Tomas Hodan

The practicality of 3D object pose estimation remains limited for many applications due to the need for prior knowledge of a 3D model and a training period for new objects. To address this limitation, we propose an approach that takes a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Van Nguyen Nguyen , Thibault Groueix , Yinlin Hu , Mathieu Salzmann , Vincent Lepetit

As robotic systems increasingly encounter complex and unconstrained real-world scenarios, there is a demand to recognize diverse objects. The state-of-the-art 6D object pose estimation methods rely on object-specific training and therefore…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Philipp Ausserlechner , David Haberger , Stefan Thalhammer , Jean-Baptiste Weibel , Markus Vincze

Learning to represent three dimensional (3D) human pose given a two dimensional (2D) image of a person, is a challenging problem. In order to make the problem less ambiguous it has become common practice to estimate 3D pose in the camera…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Mara Levy , Abhinav Shrivastava

Transformers increasingly dominate the machine learning landscape across many tasks and domains, which increases the importance for understanding their outputs. While their attention modules provide partial insight into their inner…

Computer Vision and Pattern Recognition · Computer Science 2023-01-23 Moritz Böhle , Mario Fritz , Bernt Schiele

Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation, existing methods have limited applicability in real-world scenarios involving embodied agents and downstream 3D vision tasks. These limitations mainly…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Zhiwen Fan , Panwang Pan , Peihao Wang , Yifan Jiang , Dejia Xu , Hanwen Jiang , Zhangyang Wang

Gaze following aims to interpret human-scene interactions by predicting the person's focal point of gaze. Prevailing approaches often adopt a two-stage framework, whereby multi-modality information is extracted in the initial stage for gaze…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Yuehao Song , Xinggang Wang , Jingfeng Yao , Wenyu Liu , Jinglin Zhang , Xiangmin Xu

Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurrently, large-scale vision language models show remarkable zero-shot capabilities. In this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Liming Kuang , Yordanka Velikova , Mahdi Saleh , Jan-Nico Zaech , Danda Pani Paudel , Benjamin Busam

RGB-based novel object pose estimation is critical for rapid deployment in robotic applications, yet zero-shot generalization remains a key challenge. In this paper, we introduce PicoPose, a novel framework designed to tackle this task…

Computer Vision and Pattern Recognition · Computer Science 2025-09-01 Lihua Liu , Jiehong Lin , Zhenxin Liu , Kui Jia

Rotary Position Embedding (RoPE) performs remarkably on language models, especially for length extrapolation of Transformers. However, the impacts of RoPE on computer vision domains have been underexplored, even though RoPE appears capable…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Byeongho Heo , Song Park , Dongyoon Han , Sangdoo Yun