Cross-attention of disentangled modalities for 3d human mesh recovery with transformers

J Cho, K Youwang, TH Oh - European Conference on Computer Vision, 2022 - Springer
Transformer encoder architectures have recently achieved state-of-the-art results on
monocular 3D human mesh reconstruction, but they require a substantial number of …

Convolutional mesh regression for single-image human shape reconstruction

N Kolotouros, G Pavlakos… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
This paper addresses the problem of 3D human pose and shape estimation from a single
image. Previous approaches consider a parametric model of the human body, SMPL, and …

Pose from shape: Deep pose estimation for arbitrary 3d objects

Y **ao, X Qiu, PA Langlois, M Aubry… - arxiv preprint arxiv …, 2019 - arxiv.org
Most deep pose estimation methods need to be trained for specific object instances or
categories. In this work we propose a completely generic deep pose estimation approach …

Spherical regression: Learning viewpoints, surface normals and 3d rotations on n-spheres

S Liao, E Gavves, CGM Snoek - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Many computer vision challenges require continuous outputs, but tend to be solved by
discrete classification. The reason is classification's natural containment within a probability …

[HTML][HTML] Vision-based spacecraft pose estimation via a deep convolutional neural network for noncooperative docking operations

T Phisannupawong, P Kamsing, P Torteeka… - Aerospace, 2020 - mdpi.com
The capture of a target spacecraft by a chaser is an on-orbit docking operation that requires
an accurate, reliable, and robust object recognition algorithm. Vision-based guided …