|
|
|
|
LEADER |
01000caa a22002652 4500 |
001 |
NLM373363990 |
003 |
DE-627 |
005 |
20240626232514.0 |
007 |
cr uuu---uuuuu |
008 |
240608s2024 xx |||||o 00| ||eng c |
024 |
7 |
|
|a 10.1109/TPAMI.2024.3411051
|2 doi
|
028 |
5 |
2 |
|a pubmed24n1452.xml
|
035 |
|
|
|a (DE-627)NLM373363990
|
035 |
|
|
|a (NLM)38848236
|
040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
041 |
|
|
|a eng
|
100 |
1 |
|
|a Lu, Yuqin
|e verfasserin
|4 aut
|
245 |
1 |
0 |
|a 3D Snapshot
|b Invertible Embedding of 3D Neural Representations in a Single Image
|
264 |
|
1 |
|c 2024
|
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 Revised 25.06.2024
|
500 |
|
|
|a published: Print-Electronic
|
500 |
|
|
|a Citation Status Publisher
|
520 |
|
|
|a 3D neural rendering enables photo-realistic reconstruction of a specific scene by encoding discontinuous inputs into a neural representation. Despite the remarkable rendering results, the storage of network parameters is not transmission-friendly and not extendable to metaverse applications. In this paper, we propose an invertible neural rendering approach that enables generating an interactive 3D model from a single image (i.e., 3D Snapshot). Our idea is to distill a pre-trained neural rendering model (e.g., NeRF) into a visualizable image form that can then be easily inverted back to a neural network. To this end, we first present a neural image distillation method to optimize three neural planes for representing the original neural rendering model. However, this representation is noisy and visually meaningless. We thus propose a dynamic invertible neural network to embed this noisy representation into a plausible image representation of the scene. We demonstrate promising reconstruction quality quantitatively and qualitatively, by comparing to the original neural rendering model, as well as video-based invertible methods. On the other hand, our method can store dozens of NeRFs with a compact restoration network (5MB), and embedding each 3D scene takes up only 160KB of storage. More importantly, our approach is the first solution that allows embedding a neural rendering model into image representations, which enables applications like creating an interactive 3D model from a printed image in the metaverse
|
650 |
|
4 |
|a Journal Article
|
700 |
1 |
|
|a Deng, Bailin
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Zhong, Zhixuan
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Zhang, Tianle
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Quan, Yuhui
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Cai, Hongmin
|e verfasserin
|4 aut
|
700 |
1 |
|
|a He, Shengfeng
|e verfasserin
|4 aut
|
773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g PP(2024) vom: 07. Juni
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
773 |
1 |
8 |
|g volume:PP
|g year:2024
|g day:07
|g month:06
|
856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3411051
|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 PP
|j 2024
|b 07
|c 06
|