High Dynamic Range Image Synthesis with Ghost-Free

This paper presents an efficient ghost-free approach to address the object motion problem that commonly exists in high dynamic range (HDR) image synthesis. Global illumination correction, as the first step, is to adjust the illumination of source images so that the differences between adjacent images of various expose time can be alleviated. Followed by the on-line selective composition consist of only two parameters instead of the buffer with all the pixel values in image sequence for each pixel location. With the first image being selected as a reference image, the proposed approach can start the global illumination correction and on-line selective composition process once the second image is captured without assuming the expose value (EV) known. Experimental results demonstrate that the proposed approach can yield fairly comparable results in synthesized HDR image quality as state-of-the-art approach, but the proposed approach cost much lower hardware resources.

Authors

Institutions

Publication Details

Published
2024-09-15
DOI
https://doi.org/10.1145/3689236.3696047
Citations
1
Primary Topic
Advanced Vision and Imaging
Type
article
Field-Weighted Citation Impact
0.25
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

High Dynamic Range Image Synthesis with Ghost-Free

Dengbiao Jiang, Nian Tao, K. J. Zhu
1 citations
Advanced Vision and Imaging
0.25
article

High Dynamic Range Image Synthesis with Ghost-Free

Dengbiao Jiang, Nian Tao, K. J. Zhu
article en
1 citations

Abstract

This paper presents an efficient ghost-free approach to address the object motion problem that commonly exists in high dynamic range (HDR) image synthesis. Global illumination correction, as the first step, is to adjust the illumination of source images so that the differences between adjacent images of various expose time can be alleviated. Followed by the on-line selective composition consist of only two parameters instead of the buffer with all the pixel values in image sequence for each pixel location. With the first image being selected as a reference image, the proposed approach can start the global illumination correction and on-line selective composition process once the second image is captured without assuming the expose value (EV) known. Experimental results demonstrate that the proposed approach can yield fairly comparable results in synthesized HDR image quality as state-of-the-art approach, but the proposed approach cost much lower hardware resources.

Jiangsu University of Science and Technology (CN)
Openalex Percentile: Top 44%
Advanced Vision and Imaging
0.25
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.