Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Point-based rendering enhancement via deep learning

Point-based rendering enhancement via deep learning Current state-of-the-art point rendering techniques such as splat rendering generally require very high-resolution point clouds in order to create high-quality photo realistic renderings. These can be very time consuming to acquire and oftentimes also require high-end expensive scanners. This paper proposes a novel deep learning-based approach that can generate high-resolution photo realistic point renderings from low-resolution point clouds. More specifically, we propose to use co-registered high-quality photographs as the ground truth data to train the deep neural network for point-based rendering. The proposed method can generate high-quality point rendering images very efficiently and can be used for interactive navigation of large-scale 3D scenes as well as image-based localization. Extensive quantitative evaluations on both synthetic and real datasets show that the proposed method outperforms state-of-the-art methods. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png The Visual Computer Springer Journals

Point-based rendering enhancement via deep learning

Bui, Giang; Le, Truc; Morago, Brittany; Duan, Ye
The Visual Computer , Volume 34 (8) – May 11, 2018
Download PDF
13 pages

Loading next page...
 
/lp/springer_journal/point-based-rendering-enhancement-via-deep-learning-6N92KOk2tQ
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer-Verlag GmbH Germany, part of Springer Nature
Subject
Computer Science; Computer Graphics; Computer Science, general; Artificial Intelligence (incl. Robotics); Image Processing and Computer Vision
ISSN
0178-2789
eISSN
1432-2315
DOI
10.1007/s00371-018-1550-6
Publisher site
See Article on Publisher Site

Abstract

Current state-of-the-art point rendering techniques such as splat rendering generally require very high-resolution point clouds in order to create high-quality photo realistic renderings. These can be very time consuming to acquire and oftentimes also require high-end expensive scanners. This paper proposes a novel deep learning-based approach that can generate high-resolution photo realistic point renderings from low-resolution point clouds. More specifically, we propose to use co-registered high-quality photographs as the ground truth data to train the deep neural network for point-based rendering. The proposed method can generate high-quality point rendering images very efficiently and can be used for interactive navigation of large-scale 3D scenes as well as image-based localization. Extensive quantitative evaluations on both synthetic and real datasets show that the proposed method outperforms state-of-the-art methods.

Journal

The Visual Computer – Springer Journals

Published: May 11, 2018

References

  • European Conference on Computer Vision
    Cui, Z; Chang, H; Shan, S; Zhong, B; Chen, X
  • Image super-resolution using deep convolutional networks
    Dong, C; Loy, CC; He, K; Tang, X
  • Image and video upscaling from local self-examples
    Freedman, G; Fattal, R
  • Multiple View Geometry in Computer Vision
    Hartley, R; Zisserman, A
  • Image transformation based on learning dictionaries across image spaces
    Jia, K; Wang, X; Tang, X
  • Single-image super-resolution using sparse regression and natural image prior
    Kim, KI; Kwon, Y
  • A survey of point-based techniques in computer graphics
    Kobbelt, L; Botsch, M
  • Automatic segmentation of unorganized noisy point clouds based on the gaussian map
    Liu, Y; Xiong, Y
  • Distinctive image features from scale-invariant keypoints
    Lowe, DG
  • An efficient solution to the five-point relative pose problem
    Nistér, D
  • Deep learning on point sets for 3D classification and segmentation
    Qi, CR; Su, H; Mo, K; Guibas, LJ
  • Photo tourism: exploring photo collections in 3D
    Snavely, N; Seitz, SM; Szeliski, R
  • Coupled dictionary training for image super-resolution
    Yang, J; Wang, Z; Lin, Z; Cohen, S; Huang, T
  • Image super-resolution via sparse representation
    Yang, J; Wright, J; Huang, TS; Ma, Y