Abstract

High dynamic range (HDR) images offer better visual quality by allowing a wider range of luminance and the visual experience is much closer to reality. In this paper, a scene-aware HDR image system is proposed. According to the characteristics of the scene to be captured, the proposed system will first decide whether it is necessary to activate the HDR imaging mode. If the dynamic range of the scene is limited, no HDR imaging is performed. On the other hand, two or three LDR (low dynamic range) images with different exposures are captured to render high-quality HDR images in an efficient way. Experimental results show that the proposed HDR image system is capable of generating HDR images using either two or three LDR images and comparable to some existing techniques where three LDR images are always used.

Keywords:
High dynamic range Computer vision High-dynamic-range imaging Computer science Artificial intelligence Tone mapping Luminance Dynamic range Computer graphics (images) Range (aeronautics) Image quality Visualization Image (mathematics) Engineering

Metrics

1
Cited By
0.00
FWCI (Field Weighted Citation Impact)
14
Refs
0.11
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Image Enhancement Techniques
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Advanced Vision and Imaging
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Computer Graphics and Visualization Techniques
Physical Sciences →  Computer Science →  Computer Graphics and Computer-Aided Design
© 2026 ScienceGate Book Chapters — All rights reserved.