Who left the dogs out? 3d animal reconstruction with expectation maximization in the loop

B Biggs, O Boyne, J Charles, A Fitzgibbon… - Computer Vision–ECCV …, 2020 - Springer
We introduce an automatic, end-to-end method for recovering the 3D pose and shape of
dogs from monocular internet images. The large variation in shape between dog breeds …

Mhr-net: Multiple-hypothesis reconstruction of non-rigid shapes from 2d views

H Zeng, X Yu, J Miao, Y Yang - European Conference on Computer Vision, 2022 - Springer
We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from Motion
(NRSfM). MHR-Net aims to find a set of reasonable reconstructions for a 2D view, and it also …

Robust isometric non-rigid structure-from-motion

S Parashar, D Pizarro, A Bartoli - IEEE Transactions on Pattern …, 2021 - ieeexplore.ieee.org
Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D object from
keypoint correspondences established between monocular 2D images. Current NRSfM …

Unsupervised monocular depth reconstruction of non-rigid scenes

A Takmaz, DP Paudel, T Probst… - … Conference on 3D …, 2021 - ieeexplore.ieee.org
Monocular depth reconstruction of complex and dynamic scenes is a highly challenging
problem. While for rigid scenes learning-based methods have been offering promising …

Structure from Motion with variable focal length: Interconnected fuzzy observer

R Benyoucef, H Hadj-Abdelkader… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
In this paper, a 3D point feature depth and camera focal length estimation is proposed, using
a partially calibrated low cost monocular camera. The camera intrinsic parameters are …

NRSfPP: non-rigid structure-from-perspective projection

M Sepehrinour, S Kasaei - Multimedia Tools and Applications, 2021 - Springer
A state-of-the-art algorithm for perspective projection reconstruction of non-rigid surfaces
from single-view and realistic videos is proposed. It overcomes the limitations arising from …