Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes

12/03/2019
by   Dvir Ginzburg, et al.
0

We present the first utterly self-supervised network for dense correspondence mapping between non-isometric shapes. The task of alignment in non-Euclidean domains is one of the most fundamental and crucial problems in computer vision. As 3D scanners can generate highly complex and dense models, the mission of finding dense mappings between those models is vital. The novelty of our solution is based on a cyclic mapping between metric spaces, where the distance between a pair of points should remain invariant after the full cycle. As the same learnable rules that generate the point-wise descriptors apply in both directions, the network learns invariant structures without any labels while coping with non-isometric deformations. We show here state-of-the-art-results by a large margin for a variety of tasks compared to known self-supervised and supervised methods.

READ FULL TEXT

page 1

page 4

page 8

research
07/08/2022

Pixel-level Correspondence for Self-Supervised Learning from Video

While self-supervised learning has enabled effective representation lear...
research
08/24/2023

Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects

Learning 3D shape representation with dense correspondence for deformabl...
research
02/18/2020

MAST: A Memory-Augmented Self-supervised Tracker

Recent interest in self-supervised dense tracking has yielded rapid prog...
research
11/30/2020

Dual Geometric Graph Network (DG2N) – Zero-Shot Refinement for Dense Shape Correspondence

We provide a novel new approach for aligning geometric models using a du...
research
12/06/2018

Self-supervised Learning of Dense Shape Correspondence

We introduce the first completely unsupervised correspondence learning a...
research
07/25/2017

Efficient Deformable Shape Correspondence via Kernel Matching

We present a method to match three dimensional shapes under non-isometri...
research
12/09/2021

GAN-Supervised Dense Visual Alignment

We propose GAN-Supervised Learning, a framework for learning discriminat...

Please sign up or login with your details

Forgot password? Click here to reset