Unsupervised Discovery of Parts, Structure, and Dynamics

03/12/2019
by   Zhenjia Xu, et al.
12

Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future. In this paper, we propose a novel formulation that simultaneously learns a hierarchical, disentangled object representation and a dynamics model for object parts from unlabeled videos. Our Parts, Structure, and Dynamics (PSD) model learns to, first, recognize the object parts via a layered image representation; second, predict hierarchy via a structural descriptor that composes low-level concepts into a hierarchical structure; and third, model the system dynamics by predicting the future. Experiments on multiple real and synthetic datasets demonstrate that our PSD model works well on all three tasks: segmenting object parts, building their hierarchical structure, and capturing their motion distributions.

READ FULL TEXT

page 6

page 8

page 9

page 14

page 15

research
01/01/2021

Learning the Predictability of the Future

We introduce a framework for learning from unlabeled video what is predi...
research
04/02/2020

Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image

Humans perceive the 3D world as a set of distinct objects that are chara...
research
09/13/2018

Seeing Tree Structure from Vibration

Humans recognize object structure from both their appearance and motion;...
research
08/14/2018

Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees

Images are composed as a hierarchy of object parts. We use this insight ...
research
01/26/2023

Unsupervised Volumetric Animation

We propose a novel approach for unsupervised 3D animation of non-rigid d...
research
06/19/2019

Unsupervised Learning of Object Structure and Dynamics from Videos

Extracting and predicting object structure and dynamics from videos with...
research
11/27/2020

Unsupervised part representation by Flow Capsules

Capsule networks are designed to parse an image into a hierarchy of obje...

Please sign up or login with your details

Forgot password? Click here to reset