61 citations · 105 across the 4 of their papers we have counts for
4 papers
CAT-Net: Category-Agnostic 3D Articulation Transfer from Single Image
Jasmine Collins, Anqi Liang, Jitendra Malik +2
We present a neural network approach to transfer the motion from a single image of an articulated object to a rest-state (i.e., unarticulated) 3D model. Our network learns to predi…
Rendu basé image avec contraintes sur les gradients
Grégoire Nieto, Frédéric Devernay, James Crowley
Multi-view image-based rendering consists in generating a novel view of a scene from a set of source views. In general, this works by first doing a coarse 3D reconstruction of the…
Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk
Romain Brégier, Frédéric Devernay, Laetitia Leyrit +1
While 3D object detection and pose estimation has been studied for a long time, its evaluation is not yet completely satisfactory. Indeed, existing datasets typically consist in nu…
Defining the Pose of any 3D Rigid Object and an Associated Distance
Romain Brégier, Frédéric Devernay, Laetitia Leyrit +1
The pose of a rigid object is usually regarded as a rigid transformation, described by a translation and a rotation. However, equating the pose space with the space of rigid transf…