Flash Photography Enhancement via Intrinsic Relighting

Elmar Eisemann and Frédo Durand



Our technique enhances the appearance of photographs shot in dark environments by combining a picture taken with the available light and one taken with the flash. We preserve the ambiance of the original lighting and insert the sharpness and more reliable color information from the flash image. We use the bilateral filter to decompose the two images into detail and large-scale layers. We reconstruct the image using the large scale of the available lighting and the detail of the flash. We detect and correct artifacts due to the flash shadow. Our output images provide the combined advantages of available illumination and flash photography.


paper: PDF; Presentation: PPT, PDF 6 per page, PDF 1 per page.

Go to this page to download input and output images.

Additional references

See our work on relighting, tone mapping and in general computational photography.

See also recent papers on related subject:

Georg Petschnigg, Maneesh Agrawala, Hugues Hoppe, Richard Szeliski, Michael Cohen, Kentaro Toyama. Digital Photography with Flash and No-Flash Image Pairs.ACM Transactions on Graphics (Proceedings of SIGGRAPH 2004), 2004.

Non-photorealistic Camera: Depth Edge Detection and Stylized Rendering Using a Multi-Flash Camera
Ramesh Raskar (Mitsubishi Electric Research Labs), Karhan Tan (University of Illinois at Urbana-Champaign), Rogerio Feris (University of California, Santa Barbara), Jingyi Yu (Massachusetts Institute of Technology), Matthew Turk (University of California, Santa Barbara)

Jiaya Jia, Jian Sun, Chi-Keung Tang and Heung-Yeung Shum, Bayesian Correction of Image Intensity with Spatial Consideration, 8th European Conference on Computer Vision (ECCV), May2004 , Pages III: 342 -354.

Comparison with recent work

Our approach shares many similarities with the method independently developed by Petschnigg et al. (see above). The main difference lies in the treatment of color information: Petschnigg et al. use the color information from the available-light image, while we use the color from the flash image. The tradeoff is as follows: