Dynamic Cage-Driven 3D Range-Scan Alignment

The 3D Shape Retrieval Contest 2010 (SHREC’10) on range scan retrieval aims at comparing algorithms that match a range scan to complete 3D models in a target database1. The queries

We present a new method for 3D facial meshes, using geodesic distances and non-rigid registration

Thanks to a learned boundary edge function, we are able to compute efficiently a set of motion boundaries which in fact correspond to all possible articulations of the 3D

While deformable surfaces are represented as displaced Catmull-Clark subdivision surfaces, we voxelize the actual surface geometry of rigid objects in order to determine

This paper compared non-rigid retrieval results obtained by 22 different methods, submitted by nine research groups, on two new datasets of human body models.. These datasets are

We decided to use plush toys to test the robustness of shape retrieval methods against articulated and local deformations, as they can be easily posed in different ways, present a

The objective of the SHREC’15 Range Scans based 3D Shape Retrieval track is to evaluate algorithms that match range scans of real objects to complete 3D mesh models in a

A novel method using non-rigid image registration was reported which is obtained through two steps: (i) au- tomated rigid or affine registration, and (ii) a non-rigid in- tensity