Learning 3D Object Categories by Looking Around Them

05/10/2017
by   David Novotny, et al.
0

Traditional approaches for learning 3D object categories use either synthetic data or manual supervision. In this paper, we propose a method which does not require manual annotations and is instead cued by observing objects from a moving vantage point. Our system builds on two innovations: a Siamese viewpoint factorization network that robustly aligns different videos together without explicitly comparing 3D shapes; and a 3D shape completion network that can extract the full shape of an object from partial observations. We also demonstrate the benefits of configuring networks to perform probabilistic predictions as well as of geometry-aware data augmentation schemes. We obtain state-of-the-art results on publicly-available benchmarks.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 7

page 8

page 10

page 11

research
10/17/2019

Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics

We present a convolutional neural network for joint 3D shape prediction ...
research
12/19/2021

End-to-End Learning of Multi-category 3D Pose and Shape Estimation

In this paper, we study the representation of the shape and pose of obje...
research
09/05/2019

C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion

We propose C3DPO, a method for extracting 3D models of deformable object...
research
06/09/2017

Unsupervised learning of object frames by dense equivariant image labelling

One of the key challenges of visual perception is to extract abstract mo...
research
06/20/2018

Conditional Image Generation for Learning the Structure of Visual Objects

In this paper, we consider the problem of learning landmarks for object ...
research
12/04/2020

Compositionally Generalizable 3D Structure Prediction

Single-image 3D shape reconstruction is an important and long-standing p...
research
11/26/2019

Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors

We present an automatic annotation pipeline to recover 9D cuboids and 3D...

Please sign up or login with your details

Forgot password? Click here to reset