Variational Approach for Intensity Domain Multi-exposure Image Fusion
This addresses the limitation of standard cameras in capturing high dynamic range scenes, but it is incremental as it builds on existing multi-exposure fusion methods.
The paper tackles the problem of fusing multiple low dynamic range images to produce a well-exposed image for display, achieving preservation of details in both dark and bright regions without requiring radiance reconstruction or tone manipulation.
Recent innovations shows that blending of details captured by single Low Dynamic Range (LDR) sensor overcomes the limitations of standard digital cameras to capture details from high dynamic range scene. We present a method to produce well-exposed fused image that can be displayed directly on conventional display devices. The ambition is to preserve details in poorly illuminated and brightly illuminated regions. Proposed approach does not require true radiance reconstruction and tone manipulation steps. The aforesaid objective is achieved by taking into account local information measure that select well-exposed regions across input exposures. In addition, Contrast Limited Adaptive Histogram equalization (CLAHE) is introduced to improve uniformity of input multi-exposure image prior to fusion.