| Paper Abstract and Keywords |
| Presentation |
2023-10-02 13:05
[Tutorial Invited Lecture]
From Mathematical Modeling to Data-Driven Optimization
-- Compressive Light Field Acquisition Undergoes Paradigm Shift --
Keita Takahashi (Nagoya Univ.) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
The light field is a basic representation for 3-D visual information, and it is usually treated as a set of images taken from multiple viewpoints arranged on a 2D grid with tiny intervals. The author has been working on the issue how efficiently this kind of massive information can be acquired, in particular, via compressive acquisition methods using a single computational camera equipped with optical coding capability. The traditional approach to this problem was based on the theory of compressive sensing, where some sparse structure in the target signal should explicitly be modeled. However, a paradigm shift has been caused by the recent progress of deep-learning-based approach. What dominates the scene is data-driven optimization based on deep learning, rather than the elaborate mathematical modeling of target signals. The data-driven optimization not only led to significant boost in the quality and computational speed, but also brought the capability to handle dynamic (moving) light fields. In this talk, the author will focus on the differences between the two approaches and discuss what are important in the future work. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Light Field / Coded Acquistion / Deep Learning / / / / / |
| Reference Info. |
ITE Tech. Rep., vol. 47, no. 29, 3DMT2023-35, pp. 1-1, Oct. 2023. |
| Paper # |
3DMT2023-35 |
| Date of Issue |
2023-09-25 (3DMT) |
| ISSN |
Online edition: ISSN 2424-1970 |
| Download PDF |
|
| Conference Information |
| Committee |
3DMT |
| Conference Date |
2023-10-02 - 2023-10-03 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
|
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
|
| Paper Information |
| Registration To |
3DMT |
| Conference Code |
2023-10-3DMT |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
From Mathematical Modeling to Data-Driven Optimization |
| Sub Title (in English) |
Compressive Light Field Acquisition Undergoes Paradigm Shift |
| Keyword(1) |
Light Field |
| Keyword(2) |
Coded Acquistion |
| Keyword(3) |
Deep Learning |
| Keyword(4) |
|
| Keyword(5) |
|
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Keita Takahashi |
| 1st Author's Affiliation |
Nagoya University (Nagoya Univ.) |
| 2nd Author's Name |
|
| 2nd Author's Affiliation |
() |
| 3rd Author's Name |
|
| 3rd Author's Affiliation |
() |
| 4th Author's Name |
|
| 4th Author's Affiliation |
() |
| 5th Author's Name |
|
| 5th Author's Affiliation |
() |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| Speaker |
Author-1 |
| Date Time |
2023-10-02 13:05:00 |
| Presentation Time |
60 minutes |
| Registration for |
3DMT |
| Paper # |
3DMT2023-35 |
| Volume (vol) |
vol.47 |
| Number (no) |
no.29 |
| Page |
p.1 |
| #Pages |
1 |
| Date of Issue |
2023-09-25 (3DMT) |
|