A subspace model-based approach to face relighting under unknown lighting and poses
We present a new approach to face relighting by jointly estimating the pose, reflectance functions, and lighting from as few as one image of a face. Upon such estimation, we can synthesize the face image under any prescribed new lighting condition. In contrast to commonly used face shape models or shape-dependent models, we neither recover nor assume the 3-D face shape during the estimation process. Instead, we train a pose- and pixel-dependent subspace model of the reflectance function using a face database that contains samples of pose and illumination for a large number of individuals (e.g., the CMU PIE database and the Yale database). Using this subspace model, we can estimate the pose, the reflectance functions, and the lighting condition of any given face image. Our approach lends itself to practical applications thanks to many desirable properties, including the preservation of the non-Lambertian skin reflectance properties and facial hair, as well as reproduction of various shadows on the face. Extensive experiments show that, compared to recent representative face relighting techniques, our method successfully produces better results, in terms of subjective and objective quality, without reconstructing a 3-D shape.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2008 |
|---|---|
| Erschienen: |
2008 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:17 |
|---|---|
| Enthalten in: |
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society - 17(2008), 8 vom: 01. Aug., Seite 1331-41 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Shim, Hyunjung [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 16.09.2008 Date Revised 17.07.2008 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.1109/TIP.2008.925390 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM180952072 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM180952072 | ||
| 003 | DE-627 | ||
| 005 | 20231223160355.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231223s2008 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TIP.2008.925390 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n0603.xml |
| 035 | |a (DE-627)NLM180952072 | ||
| 035 | |a (NLM)18632343 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Shim, Hyunjung |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A subspace model-based approach to face relighting under unknown lighting and poses |
| 264 | 1 | |c 2008 | |
| 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 16.09.2008 | ||
| 500 | |a Date Revised 17.07.2008 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a We present a new approach to face relighting by jointly estimating the pose, reflectance functions, and lighting from as few as one image of a face. Upon such estimation, we can synthesize the face image under any prescribed new lighting condition. In contrast to commonly used face shape models or shape-dependent models, we neither recover nor assume the 3-D face shape during the estimation process. Instead, we train a pose- and pixel-dependent subspace model of the reflectance function using a face database that contains samples of pose and illumination for a large number of individuals (e.g., the CMU PIE database and the Yale database). Using this subspace model, we can estimate the pose, the reflectance functions, and the lighting condition of any given face image. Our approach lends itself to practical applications thanks to many desirable properties, including the preservation of the non-Lambertian skin reflectance properties and facial hair, as well as reproduction of various shadows on the face. Extensive experiments show that, compared to recent representative face relighting techniques, our method successfully produces better results, in terms of subjective and objective quality, without reconstructing a 3-D shape | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Luo, Jiebo |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Tsuhan |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 17(2008), 8 vom: 01. Aug., Seite 1331-41 |w (DE-627)NLM09821456X |x 1941-0042 |7 nnns |
| 773 | 1 | 8 | |g volume:17 |g year:2008 |g number:8 |g day:01 |g month:08 |g pages:1331-41 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TIP.2008.925390 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 17 |j 2008 |e 8 |b 01 |c 08 |h 1331-41 | ||