3D-CODED : 3D Correspondences by Deep Deformation

13 Jun 2018Thibault GroueixMatthew FisherVladimir G. KimBryan C. RussellMathieu Aubry

We present a new deep learning approach for matching deformable shapes by introducing {\it Shape Deformation Networks} which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a template, that parameterizes the surface, and (ii) a learnt global feature vector that parameterizes the transformation of the template into the input surface... (read more)

PDF Abstract

Evaluation Results from the Paper


 SOTA for 3D Point Cloud Matching on Faust (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
3D Point Cloud Matching Faust 3D-CODED L2 cm # 1