TY - JOUR
T1 - CG2Real
T2 - Improving the realism of computer generated images using a large collection of photographs
AU - Johnson, Micah K.
AU - Dale, Kevin
AU - Avidan, Shai
AU - Pfister, Hanspeter
AU - Freeman, William T.
AU - Matusik, Wojciech
N1 - Funding Information:
This work was supported in part by the US National Science Foundation under Grants No. PHY-0835713 and 0739255, the John A. and Elizabeth S. Armstrong Fellowship at Harvard, and through generous support from Adobe Systems. The authors would like to thank David Salesin and Tom Malloy at Adobe for their continuing support. This work was completed while S. Avidan and W. Matusik were Senior Research Scientists at Adobe Systems.
PY - 2011
Y1 - 2011
N2 - Computer-generated (CG) images have achieved high levels of realism. This realism, however, comes at the cost of long and expensive manual modeling, and often humans can still distinguish between CG and real images. We introduce a new data-driven approach for rendering realistic imagery that uses a large collection of photographs gathered from online repositories. Given a CG image, we retrieve a small number of real images with similar global structure. We identify corresponding regions between the CG and real images using a mean-shift cosegmentation algorithm. The user can then automatically transfer color, tone, and texture from matching regions to the CG image. Our system only uses image processing operations and does not require a 3D model of the scene, making it fast and easy to integrate into digital content creation workflows. Results of a user study show that our hybrid images appear more realistic than the originals.
AB - Computer-generated (CG) images have achieved high levels of realism. This realism, however, comes at the cost of long and expensive manual modeling, and often humans can still distinguish between CG and real images. We introduce a new data-driven approach for rendering realistic imagery that uses a large collection of photographs gathered from online repositories. Given a CG image, we retrieve a small number of real images with similar global structure. We identify corresponding regions between the CG and real images using a mean-shift cosegmentation algorithm. The user can then automatically transfer color, tone, and texture from matching regions to the CG image. Our system only uses image processing operations and does not require a 3D model of the scene, making it fast and easy to integrate into digital content creation workflows. Results of a user study show that our hybrid images appear more realistic than the originals.
KW - Image enhancement
KW - image databases
KW - image-based rendering
UR - http://www.scopus.com/inward/record.url?scp=79960362333&partnerID=8YFLogxK
U2 - 10.1109/TVCG.2010.233
DO - 10.1109/TVCG.2010.233
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 21041875
AN - SCOPUS:79960362333
SN - 1077-2626
VL - 17
SP - 1273
EP - 1285
JO - IEEE Transactions on Visualization and Computer Graphics
JF - IEEE Transactions on Visualization and Computer Graphics
IS - 9
M1 - 5620893
ER -