Abstract
In this paper we present a new method for estimating the optical transmission in hazy scenes given a single input image. Based on this estimation, the scattered light is eliminated to increase scene visibility and recover haze-free scene contrasts. In this new approach we formulate a refined image formation model that accounts for surface shading in addition to the transmission function. This allows us to resolve ambiguities in the data by searching for a solution in which the resulting shading and transmission functions are locally statistically uneorrelated. A similar principle is used to estimate the color of the haze. Results demonstrate the new method abilities to remove the haze layer as well as provide a reliable transmission estimate which can be used for additional applications such as image refocusing and novel view synthesis.
Original language | English |
---|---|
State | Published - 2008 |
Event | ACM SIGGRAPH 2008 Papers 2008, SIGGRAPH'08 - Los Angeles, CA, United States Duration: 11 Aug 2008 → 15 Aug 2008 |
Conference
Conference | ACM SIGGRAPH 2008 Papers 2008, SIGGRAPH'08 |
---|---|
Country/Territory | United States |
City | Los Angeles, CA |
Period | 11/08/08 → 15/08/08 |
Keywords
- Computational photography
- Image dehazing/defogging
- Image enhancement
- Image restoration
- Markov random field image modeling