Logo image
Pseudo-Multiple-Exposure based Tone Fusion with Local Region Adjustment
Thesis

Pseudo-Multiple-Exposure based Tone Fusion with Local Region Adjustment

Chiu, Cheng-Wen
Masters, 國立清華大學, 資訊工程學系
2011

Abstract

高動態範圍 低動態範圍 反色調對映 區域加強 對比加強 High Dynamic Range (HDR) Low Dynamic Range (LDR) Tone Mapping Inverse Tone Mapping Local Region Enhancement Contrast Enhancement
New generations of display technologies provide significantly improved dynamic range over conventional display devices. Inverse tone mapping are proposed to convert low dynamic range (LDR) images to HDR ones but they generally require multiple exposure LDR images of the same scene as inputs. However, the vast majority of LDR images and videos available have only one single exposure. We propose an exposure dependent S curve to convert one normal exposure LDR image to multiple images with different brightness. The S curve enhances the mid-tone regions, avoids saturation in bright regions and boosts intensity in dark regions of an image. In addition, we propose the exposure and region dependent Gaussian weighting functions to fuse multiple images with different brightness. The fused image has enhanced detail in the bright region of the dark image and dark region of the bright image. According to our implementation results, the dynamic range can reach from 0.0001~100. Compared with other inverse tone mapped images, our results have lower visual difference and higher contrast measure. The emulated multiple exposure tone fusion method can be applied to LDR images to preserve and enhance details of the image.

Metrics

1 Record Views

Details

Logo image