|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM337667624 |
| 003 |
DE-627 |
| 005 |
20231225234934.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2022.3151997
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1125.xml
|
| 035 |
|
|
|a (DE-627)NLM337667624
|
| 035 |
|
|
|a (NLM)35235508
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhan, Fangneng
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a GMLight
|b Lighting Estimation via Geometric Distribution Approximation
|
| 264 |
|
1 |
|c 2022
|
| 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 14.03.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Inferring the scene illumination from a single image is an essential yet challenging task in computer vision and computer graphics. Existing works estimate lighting by regressing representative illumination parameters or generating illumination maps directly. However, these methods often suffer from poor accuracy and generalization. This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation. We parameterize illumination scenes in terms of the geometric light distribution, light intensity, ambient term, and auxiliary depth, which can be estimated by a regression network. Inspired by the earth mover's distance, we design a novel geometric mover's loss to guide the accurate regression of light distribution parameters. With the estimated light parameters, the generative projector synthesizes panoramic illumination maps with realistic appearance and high-frequency details. Extensive experiments show that GMLight achieves accurate illumination estimation and superior fidelity in relighting for 3D object insertion. The codes are available at https://github.com/fnzhan/Illumination-Estimation
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Yu, Yingchen
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhang, Changgong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wu, Rongliang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Hu, Wenbo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lu, Shijian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ma, Feiying
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xie, Xuansong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Shao, Ling
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 31(2022) vom: 02., Seite 2268-2278
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:02
|g pages:2268-2278
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2022.3151997
|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 31
|j 2022
|b 02
|h 2268-2278
|