activity
20182020
most citedDeep Multi-class Adversarial Specularity Removal

1 citations · 1 across the 1 of their papers we have counts for

collaborators

5 papers

math.NA2020

An Optimal Triangle Projector with Prescribed Area and Orientation, Application to Position-Based Dynamics

Carlos Arango Duque, Adrien Bartoli

The vast majority of mesh-based modelling applications iteratively transform the mesh vertices under prescribed geometric conditions. This occurs in particular in methods cycling t…

cs.CV2019

DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences

Jose Lamarca, Shaifali Parashar, Adrien Bartoli +1

Monocular SLAM algorithms perform robustly when observing rigid scenes, however, they fail when the observed scene deforms, for example, in medical endoscopy applications. We prese…

cs.CV20191 cited

Deep Multi-class Adversarial Specularity Removal

John Lin, Mohamed El Amine Seddik, Mohamed Tamaazousti +2

We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single imag…

cs.CV2018

Deep Shape-from-Template: Wide-Baseline, Dense and Fast Registration and Deformable Reconstruction from a Single Image

David Fuentes-Jimenez, David Casillas-Perez, Daniel Pizarro +2

We present Deep Shape-from-Template (DeepSfT), a novel Deep Neural Network (DNN) method for solving real-time automatic registration and 3D reconstruction of a deformable object vi…

cs.CV2018

Model-based active learning to detect isometric deformable objects in the wild with deep architectures

Shrinivasan Sankar, Adrien Bartoli

In the recent past, algorithms based on Convolutional Neural Networks (CNNs) have achieved significant milestones in object recognition. With large examples of each object class, s…