Generative Adversarial Frontal View to Bird View Synthesis

08/01/2018
by   Xinge Zhu, et al.
0

Environment perception is an important task with great practical value and bird view is an essential part for creating panoramas of surrounding environment. Due to the large gap and severe deformation between the frontal view and bird view, generating a bird view image from a single frontal view is challenging. To tackle this problem, we propose the BridgeGAN, i.e., a novel generative model for bird view synthesis. First, an intermediate view, i.e., homography view, is introduced to bridge the large gap. Next, conditioned on the three views (frontal view, homography view and bird view) in our task, a multi-GAN based model is proposed to learn the challenging cross-view translation. Extensive experiments conducted on a synthetic dataset have demonstrated that the images generated by our model are much better than those generated by existing methods, with more consistent global appearance and sharper details. Ablation studies and discussions show its reliability and robustness in some challenging cases.

READ FULL TEXT

page 7

page 8

research
04/17/2017

Multi-View Image Generation from a Single-View

This paper addresses a challenging problem -- how to generate multi-view...
research
08/14/2018

Cross-view image synthesis using geometry-guided conditional GANs

We address the problem of generating images across two drastically diffe...
research
07/20/2020

Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism

Learning to generate natural scenes has always been a daunting task in c...
research
01/19/2021

Deep View Synthesis via Self-Consistent Generative Network

View synthesis aims to produce unseen views from a set of views captured...
research
03/03/2021

ID-Unet: Iterative Soft and Hard Deformation for View Synthesis

View synthesis is usually done by an autoencoder, in which the encoder m...
research
12/05/2019

A Study into Echocardiography View Conversion

Transthoracic echo is one of the most common means of cardiac studies in...
research
03/05/2023

HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling

In this work, we tackle the challenging problem of learning-based single...

Please sign up or login with your details

Forgot password? Click here to reset