loading
Papers

Research.Publish.Connect.

Paper

Authors: Duo Chen ; Jie Feng and Bingfeng Zhou

Affiliation: Institute of Computer Science and Technology, Peking University, Beijing, China

ISBN: 978-989-758-354-4

Keyword(s): Novel View Synthesis, Depth Map, Importance Sampling, Image Projection.

Abstract: In this paper, we present a new method for synthesizing images of a 3D scene at novel viewpoints, based on a set of reference images taken in a casual manner. With such an image set as input, our method first reconstruct a sparse 3D point cloud of the scene, and then it is projected to each reference image to get a set of depth points. Afterwards, an improved error-diffusion sampling method is utilized to generate a sampling point set in each reference image, which includes the depth points and preserves the image features well. Therefore the image can be triangulated on the basis of the sampling point set. Then, we propose a distance metric based on Euclidean distance, color similarity and boundary distribution to propagate depth information from the depth points to the rest of sampling points, and hence a dense depth map can be generated by interpolation in the triangle mesh. Given a desired viewpoint, several closest reference viewpoints are selected, and their colored depth maps a re projected to the novel view. Finally, multiple projected images are merged to fill the holes caused by occusion, and result in a complete novel view. Experimental results demonstrate that our method can achieve high quality results for outdoor scenes that contain challenging objects. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 100.24.122.228

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Chen, D.; Feng, Jie and Zhou, B. (2019). Novel View Synthesis using Feature-preserving Depth Map Resampling.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP, ISBN 978-989-758-354-4, pages 193-200. DOI: 10.5220/0007308701930200

@conference{grapp19,
author={Duo Chen. and Feng, Jie and Bingfeng Zhou.},
title={Novel View Synthesis using Feature-preserving Depth Map Resampling},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,},
year={2019},
pages={193-200},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007308701930200},
isbn={978-989-758-354-4},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 1: GRAPP,
TI - Novel View Synthesis using Feature-preserving Depth Map Resampling
SN - 978-989-758-354-4
AU - Chen, D.
AU - Feng, Jie
AU - Zhou, B.
PY - 2019
SP - 193
EP - 200
DO - 10.5220/0007308701930200

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.