Objects as points

X Zhou, D Wang, P Krähenbühl - arxiv preprint arxiv:1904.07850, 2019 - arxiv.org
Detection identifies objects as axis-aligned boxes in an image. Most successful object
detectors enumerate a nearly exhaustive list of potential object locations and classify each …

Cdpn: Coordinates-based disentangled pose network for real-time rgb-based 6-dof object pose estimation

Z Li, G Wang, X Ji - Proceedings of the IEEE/CVF …, 2019 - openaccess.thecvf.com
DoF object pose estimation from a single RGB image is a fundamental and long-standing
problem in computer vision. Current leading approaches solve it by training deep networks …

Hybridpose: 6d object pose estimation under hybrid representations

C Song, J Song, Q Huang - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes
a hybrid intermediate representation to express different geometric information in the input …

Templates for 3d object pose estimation revisited: Generalization to new objects and robustness to occlusions

VN Nguyen, Y Hu, Y **ao… - Proceedings of the …, 2022 - openaccess.thecvf.com
We present a method that can recognize new objects and estimate their 3D pose in RGB
images even under partial occlusions. Our method requires neither a training phase on …

Zero-shot category-level object pose estimation

W Goodwin, S Vaze, I Havoutis, I Posner - European Conference on …, 2022 - Springer
Object pose estimation is an important component of most vision pipelines for embodied
agents, as well as in 3D vision more generally. In this paper we tackle the problem of …

Pose for everything: Towards category-agnostic pose estimation

L Xu, S **, W Zeng, W Liu, C Qian, W Ouyang… - European conference on …, 2022 - Springer
Existing works on 2D pose estimation mainly focus on a certain category, eg human, animal,
and vehicle. However, there are lots of application scenarios that require detecting the …

CenterFace: joint face detection and alignment using face as point

Y Xu, W Yan, G Yang, J Luo, T Li… - Scientific Programming, 2020 - Wiley Online Library
Face detection and alignment in unconstrained environment is always deployed on edge
devices which have limited memory storage and low computing power. This paper proposes …