Abstract | ||
---|---|---|
Many recent computational photography techniques decompose an image into a piecewise smooth base layer, containing large scale variations in intensity, and a residual detail layer capturing the smaller scale details in the image. In many of these applications, it is important to control the spatial scale of the extracted details, and it is often desirable to manipulate details at multiple scales, while avoiding visual artifacts. In this paper we introduce a new way to construct edge-preserving multi-scale image decompositions. We show that current base- detail decomposition techniques, based on the bilateral filter, are limited in their ability to extract detail at arbitrary scales. Instead, we advocate the use of an alternative edge-preserving smoothing operator, based on the weighted least squares optimization frame- work, which is particularly well suited for progressive coarsening of images and for multi-scale detail extraction. After describing this operator, we show how to use it to construct edge-preserving multi-scale decompositions, and compare it to the bilateral filter, as well as to other schemes. Finally, we demonstrate the effectiveness of our edge-preserving decompositions in the context of LDR and HDR tone mapping, detail enhancement, and other applications. CR Categories: I.3.3 (Computer Graphics): Picture/Image Generation—Display algorithms; I.4.3 (Image Processing and Computer Vision): Enhancement—Grayscale Manipulation; I.4.9 (Image Processing and Computer Vision): Applications; |
Year | DOI | Venue |
---|---|---|
2008 | 10.1145/1360612.1360666 | ACM Trans. Graph. |
Keywords | Field | DocType |
spatial scale,tone mapping,bilateral filtering | Computer vision,Visual artifact,Computer graphics (images),Computer science,Computational photography,Smoothing,Tone mapping,Artificial intelligence,Operator (computer programming),Bilateral filter,Piecewise,Edge-preserving smoothing | Journal |
Volume | Issue | ISSN |
27 | 3 | 0730-0301 |
Citations | PageRank | References |
422 | 12.08 | 35 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zeev Farbman | 1 | 789 | 27.40 |
Raanan Fattal | 2 | 2440 | 119.13 |
Dani Lischinski | 3 | 5465 | 340.85 |
Richard Szeliski | 4 | 21300 | 2104.74 |