|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM35520259X |
| 003 |
DE-627 |
| 005 |
20250304150743.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3232502
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1183.xml
|
| 035 |
|
|
|a (DE-627)NLM35520259X
|
| 035 |
|
|
|a (NLM)37015513
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Yuan, Yu-Jie
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Neural Radiance Fields From Sparse RGB-D Images for High-Quality View Synthesis
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 06.06.2023
|
| 500 |
|
|
|a Date Revised 06.06.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a The recently proposed neural radiance fields (NeRF) use a continuous function formulated as a multi-layer perceptron (MLP) to model the appearance and geometry of a 3D scene. This enables realistic synthesis of novel views, even for scenes with view dependent appearance. Many follow-up works have since extended NeRFs in different ways. However, a fundamental restriction of the method remains that it requires a large number of images captured from densely placed viewpoints for high-quality synthesis and the quality of the results quickly degrades when the number of captured views is insufficient. To address this problem, we propose a novel NeRF-based framework capable of high-quality view synthesis using only a sparse set of RGB-D images, which can be easily captured using cameras and LiDAR sensors on current consumer devices. First, a geometric proxy of the scene is reconstructed from the captured RGB-D images. Renderings of the reconstructed scene along with precise camera parameters can then be used to pre-train a network. Finally, the network is fine-tuned with a small number of real captured images. We further introduce a patch discriminator to supervise the network under novel views during fine-tuning, as well as a 3D color prior to improve synthesis quality. We demonstrate that our method can generate arbitrary novel views of a 3D scene from as few as 6 RGB-D images. Extensive experiments show the improvements of our method compared with the existing NeRF-based methods, including approaches that also aim to reduce the number of input images
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Lai, Yu-Kun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Huang, Yi-Hua
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Kobbelt, Leif
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Gao, Lin
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 7 vom: 08. Juli, Seite 8713-8728
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnas
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:7
|g day:08
|g month:07
|g pages:8713-8728
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3232502
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 7
|b 08
|c 07
|h 8713-8728
|