CSDL Home IEEE Transactions on Visualization & Computer Graphics 2011 vol.17 Issue No.09 - September
Issue No.09 - September (2011 vol.17)
Micah K. Johnson , Massachusetts Institute of Technology, Cambridge
Kevin Dale , Harvard University, Cambridge
Shai Avidan , Tel Aviv University, Israel, and Adobe Systems
Hanspeter Pfister , Harvard University, Cambridge
William T. Freeman , Massachusetts Institute of Technology, Cambridge
Wojciech Matusik , Massachusetts Institute of Technology, Cambridge
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2010.233
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.
Image enhancement, image databases, image-based rendering.
Micah K. Johnson, Kevin Dale, Shai Avidan, Hanspeter Pfister, William T. Freeman, Wojciech Matusik, "CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of Photographs", IEEE Transactions on Visualization & Computer Graphics, vol.17, no. 9, pp. 1273-1285, September 2011, doi:10.1109/TVCG.2010.233