Open Access
,
страницы 523-540
Convolutional Occupancy Networks
Songyou Peng
1, 2
,
Michael Niemeyer
2, 3
,
Lars Mescheder
2, 4
,
MARC POLLEFEYS
1, 5
,
Andreas Geiger
2, 3
4
Amazon, Tübingen, Germany
|
5
Microsoft, Zurich, Switzerland
|
Тип публикации: Book Chapter
Дата публикации: 2020-12-02
scimago Q2
SJR: 0.352
CiteScore: 2.4
Impact factor: —
ISSN: 03029743, 16113349, 18612075, 18612083
Краткое описание
Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not scale to more complicated or large-scale scenes. The key limiting factor of implicit methods is their simple fully-connected network architecture which does not allow for integrating local information in the observations or incorporating inductive biases such as translational equivariance. In this paper, we propose Convolutional Occupancy Networks, a more flexible implicit representation for detailed reconstruction of objects and 3D scenes. By combining convolutional encoders with implicit occupancy decoders, our model incorporates inductive biases, enabling structured reasoning in 3D space. We investigate the effectiveness of the proposed representation by reconstructing complex geometry from noisy point clouds and low-resolution voxel representations. We empirically find that our method enables the fine-grained implicit 3D reconstruction of single objects, scales to large indoor scenes, and generalizes well from synthetic to real data.
Найдено
Ничего не найдено, попробуйте изменить настройки фильтра.
Найдено
Ничего не найдено, попробуйте изменить настройки фильтра.
Топ-30
Журналы
|
10
20
30
40
50
60
70
80
90
|
|
|
Lecture Notes in Computer Science
81 публикация, 15.43%
|
|
|
IEEE Transactions on Pattern Analysis and Machine Intelligence
27 публикаций, 5.14%
|
|
|
IEEE Transactions on Visualization and Computer Graphics
21 публикация, 4%
|
|
|
ACM Transactions on Graphics
19 публикаций, 3.62%
|
|
|
IEEE Access
9 публикаций, 1.71%
|
|
|
IEEE Robotics and Automation Letters
8 публикаций, 1.52%
|
|
|
Computers and Graphics
6 публикаций, 1.14%
|
|
|
Remote Sensing
5 публикаций, 0.95%
|
|
|
Computer Graphics Forum
4 публикации, 0.76%
|
|
|
IEEE Transactions on Image Processing
4 публикации, 0.76%
|
|
|
IEEE Transactions on Multimedia
4 публикации, 0.76%
|
|
|
IEEE Transactions on Circuits and Systems for Video Technology
3 публикации, 0.57%
|
|
|
IEEE Transactions on Robotics
3 публикации, 0.57%
|
|
|
Graphical Models
3 публикации, 0.57%
|
|
|
ISPRS Journal of Photogrammetry and Remote Sensing
3 публикации, 0.57%
|
|
|
Medical Image Analysis
3 публикации, 0.57%
|
|
|
Communications in Computer and Information Science
3 публикации, 0.57%
|
|
|
International Journal of Computer Vision
3 публикации, 0.57%
|
|
|
IEEE Transactions on Medical Imaging
3 публикации, 0.57%
|
|
|
Journal of Electronic Imaging
2 публикации, 0.38%
|
|
|
Sensors
2 публикации, 0.38%
|
|
|
IEEE Sensors Journal
2 публикации, 0.38%
|
|
|
Pattern Recognition
2 публикации, 0.38%
|
|
|
ACM Computing Surveys
2 публикации, 0.38%
|
|
|
IEEE Transactions on Geoscience and Remote Sensing
2 публикации, 0.38%
|
|
|
IEEE Signal Processing Letters
2 публикации, 0.38%
|
|
|
Computer Animation and Virtual Worlds
2 публикации, 0.38%
|
|
|
Displays
2 публикации, 0.38%
|
|
|
Mathematics
1 публикация, 0.19%
|
|
|
10
20
30
40
50
60
70
80
90
|
Издатели
|
50
100
150
200
250
300
350
|
|
|
Institute of Electrical and Electronics Engineers (IEEE)
321 публикация, 61.14%
|
|
|
Springer Nature
96 публикаций, 18.29%
|
|
|
Association for Computing Machinery (ACM)
40 публикаций, 7.62%
|
|
|
Elsevier
32 публикации, 6.1%
|
|
|
MDPI
12 публикаций, 2.29%
|
|
|
Wiley
6 публикаций, 1.14%
|
|
|
SPIE-Intl Soc Optical Eng
4 публикации, 0.76%
|
|
|
Taylor & Francis
2 публикации, 0.38%
|
|
|
Tsinghua University Press
1 публикация, 0.19%
|
|
|
SAGE
1 публикация, 0.19%
|
|
|
World Scientific
1 публикация, 0.19%
|
|
|
Bentham Science Publishers Ltd.
1 публикация, 0.19%
|
|
|
Cold Spring Harbor Laboratory
1 публикация, 0.19%
|
|
|
50
100
150
200
250
300
350
|
- Мы не учитываем публикации, у которых нет DOI.
- Статистика публикаций обновляется еженедельно.
Вы ученый?
Создайте профиль, чтобы получать персональные рекомендации коллег, конференций и новых статей.
Метрики
525
Всего цитирований:
525
Цитирований c 2024:
283
(53.91%)
Цитировать
ГОСТ |
RIS |
BibTex
Цитировать
ГОСТ
Скопировать
Peng S. et al. Convolutional Occupancy Networks // Lecture Notes in Computer Science. 2020. pp. 523-540.
ГОСТ со всеми авторами (до 50)
Скопировать
Peng S., Niemeyer M., Mescheder L., POLLEFEYS M., Geiger A. Convolutional Occupancy Networks // Lecture Notes in Computer Science. 2020. pp. 523-540.
Цитировать
RIS
Скопировать
TY - GENERIC
DO - 10.1007/978-3-030-58580-8_31
UR - https://doi.org/10.1007/978-3-030-58580-8_31
TI - Convolutional Occupancy Networks
T2 - Lecture Notes in Computer Science
AU - Peng, Songyou
AU - Niemeyer, Michael
AU - Mescheder, Lars
AU - POLLEFEYS, MARC
AU - Geiger, Andreas
PY - 2020
DA - 2020/12/02
PB - Springer Nature
SP - 523-540
SN - 0302-9743
SN - 1611-3349
SN - 1861-2075
SN - 1861-2083
ER -
Цитировать
BibTex (до 50 авторов)
Скопировать
@incollection{2020_Peng,
author = {Songyou Peng and Michael Niemeyer and Lars Mescheder and MARC POLLEFEYS and Andreas Geiger},
title = {Convolutional Occupancy Networks},
publisher = {Springer Nature},
year = {2020},
pages = {523--540},
month = {dec}
}