High Dynamic Range Imaging via Robust Multi-Exposure Image Fusion

Transform a smart-phone into a high-end camera

Multi-exposure image fusion (MEF) can produce an image with high dynamic range (HDR) effect by fusing multiple images with different exposures. The conventional MEF methods require significant pre/post-processing steps to improve the visual quality by reducing spatial artifacts. These methods may produce unwanted artifacts because of the limited processing power of mobile devices and complexities of real scenes. PolyU’s new MEF method decomposes an image patch into three conceptually independent components: signal strength, signal structure and mean intensity. By fusing these components separately, this approach can produce fused images with more vivid color appearances and fewer artifacts in both static and dynamic situations.

Top row: 3 images of a dynamic scene under different exposures. Bottom row: visual comparison between our method (right) and current state-of-the-art methods (left and middle)

Top row: 6 images of a static scene under different exposures. Bottom row: visual comparison between our method (right) and current state-of-the-art methods (left and middle)

Special Features and Advantages

Accuracy: Reconstruct HDR images with detailed structures
Robustness: Produce visually appealing results with very few artifacts
Flexibility: Can be applied to both static and dynamic scenes

Applications

HDR imaging in consumer grade digital cameras
HDR imaging in smart-phones
Image and video enhancement

Principal Investigator

Prof. Lei Zhang

Department of Computing

Download PDF version