ABSTRACT
In this paper, we propose a framework for rendering synthetic fog into interior and exterior photographs. Given a single photograph as input, our approach first obtains an approximation of the illumination and geometry for the underlying scene with a few user assistance, then generates a Transmittance Map (TMap) and a Volumetric Map (VMap) for the input photograph according to a decomposition of reflective radiance and transmittance, finally synthesizes the foggy photograph by combining the input photograph, the Transmittance Map and the Volumetric Map. Our approach employs physically based rendering technique and take into account not only the effect of increasing illumination in shadow areas and desaturation of surface reflection but also glow around the area lights and light shafts for directional lights. Compared with the previous image processing method, our approach can produce more realistic results. In addition, we demonstrate in a user study that synthetic images produced by our approach are confusable with real photographs.
- Alnasser, M., and Foroosh, H. 2006. Image-based rendering of synthetic diffuse objects in natural scenes. In Proceedings of the 18th International Conference on Pattern Recognition - Volume 04, IEEE Computer Society, Washington, DC, USA, ICPR '06, 787--790. Google ScholarDigital Library
- Cerezo, E., Perez-Cazorla, F., Pueyo, X., Seron, F., and Sillion, F. X. 2005. A Survey on Participating Media Rendering Techniques. Visual Computer.Google Scholar
- Cossairt, O., Nayar, S., and Ramamoorthi, R. 2008. Light field transfer: global illumination between real and synthetic objects. ACM Trans. Graph. 27, 3 (Aug.), 57:1--57:6. Google ScholarDigital Library
- Debevec, P. 1998. Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography. In Proceedings of the 25th annual conference on Computer graphics and interactive techniques, ACM, New York, NY, USA, SIGGRAPH '98, 189--198. Google ScholarDigital Library
- Glassner, A. 1995. Principles of digital image synthesis. The Morgan Kaufmann Series in Computer Graphics and Geometric Modeling. Morgan Kaufmann. Google ScholarDigital Library
- Hartley, R. I., and Zisserman, A. 2004. Multiple View Geometry in Computer Vision, second ed. Cambridge University Press, ISBN: 0521540518. Google ScholarDigital Library
- Hoiem, D., Efros, A. A., and Hebert, M. 2007. Recovering surface layout from an image. Int. J. Comput. Vision 75, 1 (Oct.), 151--172. Google ScholarDigital Library
- Jensen, H. W., and Christensen, P. H. 1998. Efficient simulation of light transport in scences with participating media using photon maps. In Proceedings of the 25th annual conference on Computer graphics and interactive techniques, ACM, New York, NY, USA, SIGGRAPH '98, 311--320. Google ScholarDigital Library
- Jorge, L.-M., Angel, C., and Diego, G. 2008. Image-based participating media. In CEIG 08, 179--187.Google Scholar
- Kajiya, J. T. 1986. The rendering equation. SIGGRAPH Comput. Graph. 20, 4 (Aug.), 143--150. Google ScholarDigital Library
- Karsch, K., Hedau, V., Forsyth, D., and Hoiem, D. 2011. Rendering synthetic objects into legacy photographs. ACM Trans. Graph. 30, 6 (Dec.), 157:1--157:12. Google ScholarDigital Library
- Lafortune, E. P., and Willems, Y. D. 1996. Rendering participating media with bidirectional path tracing. In Proceedings of the eurographics workshop on Rendering techniques '96, Springer-Verlag, London, UK, UK, 91--100. Google ScholarDigital Library
- Lalonde, J.-F., Efros, A. A., and Narasimhan, S. G. 2009. Estimating natural illumination from a single outdoor image. In ICCV, IEEE, 183--190.Google Scholar
- Lalonde, J.-F., Efros, A. A., and Narasimhan, S. G. 2009. Webcam clip art: appearance and illuminant transfer from time-lapse sequences. ACM Trans. Graph. 28, 5, 131:1--131:10. Google ScholarDigital Library
- Lalonde, J.-F., Efros, A. A., and Narasimhan, S. G. 2009. Webcam clip art: appearance and illuminant transfer from time-lapse sequences. ACM Trans. Graph. 28, 5 (Dec.), 131:1--131:10. Google ScholarDigital Library
- Lalonde, J.-F., Efros, A. A., and Narasimhan, S. G. 2012. Estimating the natural illumination conditions from a single outdoor image. International Journal of Computer Vision 98, 2, 123--145. Google ScholarDigital Library
- Liu, Y., Qin, X., Xu, S., Nakamae, E., and Peng, Q. 2009. Light source estimation of outdoor scenes for mixed reality. Vis. Comput. 25, 5--7 (Apr.), 637--646. Google ScholarDigital Library
- Pauly, M., Kollig, T., and Keller, A. 2000. Metropolis light transport for participating media. In Proceedings of the Eurographics Workshop on Rendering Techniques 2000, Springer-Verlag, London, UK, UK, 11--22. Google ScholarDigital Library
- Pharr, M., and Humphreys, G. 2010. Physically Based Rendering, Second Edition: From Theory To Implementation, 2nd ed. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA. Google ScholarDigital Library
- Siegel, R., and Howell, J. 1992. Thermal Radiation Heat Transfer. Hemisphere.Google Scholar
- Xing, G., Liu, Y., Qin, X., and Peng, Q. 2012. A practical approach for real-time illumination estimation of outdoor videos. Computers & Graphics 36, 7, 857--865. Google ScholarDigital Library
- Zheng, Y., Chen, X., Cheng, M.-M., Zhou, K., Hu, S.-M., and Mitra, N. J. 2012. Interactive images: Cuboid proxies for smart image manipulation. ACM Transactions on Graphics 31, 4, 99:1--99:11. Google ScholarDigital Library
Index Terms
Render synthetic fog into interior and exterior photographs
Recommendations
Making bas-reliefs from photographs of human faces
Bas-reliefs are a form of flattened artwork, part-way between 3D sculpture and 2D painting. Recent research has considered automatic bas-relief generation from 3D scenes. However, little work has addressed the generation of bas-reliefs from 2D images. ...
Hair image generation using connected texels
AbstractGeneration of photo-realistic images of human hair is a challenging topic in computer graphics. The difficulty in solving the problem in this aspect comes mainly from the extremely large number of hairs and the high complexity of the hair shapes. ...
Rendering synthetic objects into legacy photographs
SA '11: Proceedings of the 2011 SIGGRAPH Asia ConferenceWe propose a method to realistically insert synthetic objects into existing photographs without requiring access to the scene or any additional scene measurements. With a single image and a small amount of annotation, our method creates a physical model ...
Comments