Local Laplacian Filters: Edge-aware Image Processing with a Laplacian Pyramid

ACM Transactions on Graphics (Proceedings of SIGGRAPH 2011)
Sylvain Paris, Adobe
Samuel W. Hasinoff, Toyota Technological Institute at Chicago and MIT CSAIL
Jan Kautz, University College London

Back to the main page

We provide sample results of our filters applied with a wide range of parameters.

Detail manipulation

Click on the thumbnails to see sample results of our detail manipulation filter. These results were produced by a script that applied the same parameters to all the images, without any manual tweaking. A few images are noisy or contain JPEG artifacts; when increasing the amplitude of details (α<1), our filter sometimes makes these degradations more visible. This issue is common to all detail-enhancing filters.

Tone mapping

Click on the thumbnails to see sample results of our tone mapping operator. The same parameters were applied to all images, without manual tweaking or applying a "beautifying curve". Note that some results reveal imperfections in the input images, as scenes captured with real cameras sometimes have. For instance, the hotel lobby and snowman have color fringes, the kitchen and doll show lens flare, the trees behind the blue cow are blurry because they moved during capture, and the astronomy image has scanning streaks. Fixing these issues is outside the scope of our work, but our method is tolerant to them and nonetheless achieves high-quality results.

We also show a few of these examples processed at high resolution.

Inverse tone mapping

Click on the thumbnails to download our result in Radiance HDR format.