Skip to search formSkip to main contentSkip to account menu

EPnP: An Accurate O(n) Solution to the PnP Problem

A non-iterative solution to the PnP problem—the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences—whose computational complexity grows linearly with n, which can be done in O(n) time by expressing these coordinates as weighted sum of the eigenvectors of a 12×12 matrix.
View on Springer (opens in a new tab)

Discriminative Learning of Deep Convolutional Feature Point Descriptors

This paper uses Convolutional Neural Networks to learn discriminant patch representations and in particular train a Siamese network with pairs of (non-)corresponding patches to develop 128-D descriptors whose euclidean distances reflect patch similarity and can be used as a drop-in replacement for any task involving SIFT.
View on IEEE (opens in a new tab)

GANimation: Anatomically-aware Facial Animation from a Single Image

A novel GAN conditioning scheme based on Action Units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression, and proposes a fully unsupervised strategy to train the model, that only requires images annotated with their activated AUs.
View on PubMed (opens in a new tab)

D-NeRF: Neural Radiance Fields for Dynamic Scenes

D-NeRF is introduced, a method that extends neural radiance fields to a dynamic domain, allowing to reconstruct and render novel images of objects under rigid and non-rigid motions from a single camera moving around the scene.
View on IEEE (opens in a new tab)

3D Human Pose Estimation from a Single Image via Distance Matrix Regression

  • F. Moreno-Noguer
  • Computer Science
    Computer Vision and Pattern Recognition
  • 28 November 2016
It is shown that more precise pose estimates can be obtained by representing both the 2D and 3D human poses using NxN distance matrices, and formulating the problem as a 2D-to-3D distance matrix regression.
View on IEEE (opens in a new tab)

PL-SLAM: Real-time monocular visual SLAM with points and lines

This paper builds upon ORB-SLAM, presumably the current state-of-the-art solution both in terms of accuracy as efficiency, and extends its formulation to simultaneously handle both point and line correspondences, and demonstrates that the use of lines does not only improve the performance of the original ORB -SLAM solution in poorly textured frames, but also systematically improves it in sequence frames combining points and lines, without compromising the efficiency.
View on IEEE (opens in a new tab)

Very Fast Solution to the PnP Problem with Algebraic Outlier Rejection

Since the outlier removal process is based on an algebraic criterion which does not require computing the full-pose and reprojecting back all 3D points on the image plane at each step, the solution achieves speed gains of more than 100× compared to RANSAC strategies.
View on IEEE (opens in a new tab)

Accurate Non-Iterative O(n) Solution to the PnP Problem

A non-iterative solution to the PnP problem-the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences-whose computational complexity grows linearly with n, which can be done in O(n) time by expressing these coordinates as weighted sum of the eigenvectors of a 12 x12 matrix.
View on IEEE (opens in a new tab)

Neuroaesthetics in fashion: Modeling the perception of fashionability

A Conditional Random Field model is proposed that jointly reasons about several fashionability factors such as thetype of outfit and garments the user is wearing, the type of the user, the photograph's setting, and the fashionability score, and is able to give rich feedback back to the user.
View on IEEE (opens in a new tab)

GANimation: One-Shot Anatomically Consistent Facial Animation

This work introduces a novel GAN conditioning scheme based on action units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression, and proposes a weakly supervised strategy to train the model, that only requires images annotated with their activated AUs.
View on Springer (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)