Shape from Shading through Shape Evolution

12/08/2017
by   Dawei Yang, et al.
0

In this paper, we address the shape-from-shading problem by training deep networks with synthetic images. Unlike conventional approaches that combine deep learning and synthetic imagery, we propose an approach that does not need any external shape dataset to render synthetic images. Our approach consists of two synergistic processes: the evolution of complex shapes from simple primitives, and the training of a deep network for shape-from-shading. The evolution generates better shapes guided by the network training, while the training improves by using the evolved shapes. We show that our approach achieves state-of-the-art performance on a shape-from-shading benchmark.

READ FULL TEXT

page 2

page 6

page 8

research
09/25/2014

Deep Learning Representation using Autoencoder for 3D Shape Retrieval

We study the problem of how to build a deep learning representation for ...
research
02/10/2023

A function space perspective on stochastic shape evolution

Modelling randomness in shape data, for example, the evolution of shapes...
research
07/26/2022

A Kendall Shape Space Approach to 3D Shape Estimation from 2D Landmarks

3D shapes provide substantially more information than 2D images. However...
research
06/29/2019

Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

Synthetic images rendered by graphics engines are a promising source for...
research
08/17/2016

A Perceptual Aesthetics Measure for 3D Shapes

While the problem of image aesthetics has been well explored, the study ...
research
03/09/2021

Knowledge Evolution in Neural Networks

Deep learning relies on the availability of a large corpus of data (labe...
research
05/26/2020

A Deep Learning based Fast Signed Distance Map Generation

Signed distance map (SDM) is a common representation of surfaces in medi...

Please sign up or login with your details

Forgot password? Click here to reset