High Dynamic Range Image Hallucination

• Lvdi Wang^1,2
• Li-Yi Wei¹
• Kun Zhou¹
• Baining Guo^1,2
• Heung-Yeung Shum^1,2

• ¹Microsoft Research Asia
• ²Tsinghua University

Abstract

We introduce high dynamic range image hallucination for adding high dynamic range details to the over-exposed and under-exposed regions of a low dynamic range image. Our method is based on a simple assumption: there exist high quality patches in the image with similar textures as the regions that are over or under exposed. Hence, we can add high dynamic range details to a region by simply transferring texture details from another patch that may be under different illumination levels. In our approach, a user only needs to annotate the image with a few strokes to indicate textures that can be applied to the corresponding under-exposed or over-exposed regions, and these regions are automatically hallucinated by our algorithm. Experiments demonstrate that our simple, yet effective approach is able to significantly increase the amount of texture details in a wide range of common scenarios, with a modest amount of user interaction.

Keywords

High Dynamic Range, Image Hallucination, Texture Synthesis

Downloads

Acknowledgements

We would like to thank Josh Bao for his participation in the early stage of this project, Becky Sundling for video dubbing, Dwight Daniels for suggestions on writing styles, and anonymous reviewers for their comments.