PX-NET: Simple, Efficient Pixel-Wise Training of Photometric Stereo Networks

by   Fotios Logothetis, et al.

Retrieving accurate 3D reconstructions of objects from the way they reflect light is a very challenging task in computer vision. Despite more than four decades since the definition of the Photometric Stereo problem, most of the literature has had limited success when global illumination effects such as cast shadows, self-reflections and ambient light come into play, especially for specular surfaces. Recent approaches have leveraged the power of deep learning in conjunction with computer graphics in order to cope with the need of a vast number of training data in order to invert the image irradiance equation and retrieve the geometry of the object. However, rendering global illumination effects is a slow process which can limit the amount of training data that can be generated. In this work we propose a novel pixel-wise training procedure for normal prediction by replacing the training data of globally rendered images with independent per-pixel renderings. We show that robustness to global physical effects can be achieved via data-augmentation which greatly simplifies and speeds up the data creation procedure. Our network, PX-NET, achieves the state-of-the-art performance on synthetic datasets, as well as the Diligent real dataset.


page 2

page 6

page 8

page 11

page 14

page 21

page 22


A CNN Based Approach for the Point-Light Photometric Stereo Problem

Reconstructing the 3D shape of an object using several images under diff...

A CNN Based Approach for the Near-Field Photometric Stereo Problem

Reconstructing the 3D shape of an object using several images under diff...

LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo

Three-dimensional reconstruction of objects from shading information is ...

Anatomical Data Augmentation For CNN based Pixel-wise Classification

In this work we propose a method for anatomical data augmentation that i...

Pixel-wise rational model for structured light system

This Letter presents a novel structured light system model that effectiv...

Learning Neural Light Transport

In recent years, deep generative models have gained significance due to ...

Refining 6D Object Pose Predictions using Abstract Render-and-Compare

Robotic systems often require precise scene analysis capabilities, espec...

Please sign up or login with your details

Forgot password? Click here to reset