Home | Research | Publications | People | School | University | Download | Join Us

Examples of Our Work

Interactive visual information processing, interactive image retrieval, segmentation .... (link ...)

Example-based Image Processing  ...  (link ...)

Unifying histogram-based image content descriptor for content-based image retrieval - the CPAM and AI framework  ... (link ...)

Integrated framework for image coding, indexing, and content-based image retrieval ... (link ...)

Visual guided browsing and navigation for fast image retrieval ... (link...)

Fast comprehensive tone mapping for high dynamic range image visualization ...

Colorizing black and white photos ... (link ....)

Making beautiful pictures,  computational photography ... (link ....)

Machine learning, pattern recognition ... (link ...)

Image data mining, image and feature co-clustering .... (link ...)


An example of a high dynamic range image rendered with one of our latest techniques. HDR radiance map courtesy of Raanan Fattal, Dani Lischinski and Michael Werman of  The Hebrew University of Jerusalem

High dynamic range image and video

We are interested in high dynamic range image and video technologies, including, dynamic range compression, tone mapping, rendering, display, visualization, coding and compression. We have developed several successful methods for visualizing high dynamic range images. A piece of very easy to use and very fast high dynamic range image display software (MS-Windows version) is also made available for free download

J Duan, G. Qiu and M. Chen, "Comprehensive Fast Tone Mapping for High Dynamic
Range Image Visualization", Pacific Graphics 2005 (PDF)

Image reproduction is a highly subjective process and different users will have very different preferences even for the same image. Therefore, a really useful tone-mapping tool for high dynamic range images should be fast and interactive, with which users can interactively adjust the mapping parameters and instantly visualize the results. Furthermore, there should be as few adjustable parameters as possible, and equally important, the parameters should have a clear, intuitive and straightforward relationship with the appearance of the mapped images to guide the users to adjust the parameters. Based on these requirements, we have developed a comprehensive tone reproduction curve based mapping technology. Our technique has two intuitive variables, which can be adjusted at an interactive speed even for very large images. One parameter controls the overall brightness of the reproduction and the other adjusts the detail and contrast  of the result.

Here is another example image rendered using one of our methods (A high dynamic range panoramic image from the Ladybug Camera we bought recently, click the image to see the full size version)


Our other related high dynamic range image visualization technologies include

G Qiu and J. Duan, "Hierarchical tone mapping for high dynamic range image  visualization", VCIP2005, Visual Communication and Image Processing, 12 - 15 July 2005, Beijing, China (PDF)
G. Qiu and J Duan,"An optimal tone reproduction curve operator for the display of high dynamic range images", ISCAS2005, IEEE International Symposium on Circuits and Systems, 23 - 26 May 2005, Kobe, Japan (PDF)
J. Duan and G. Qiu, "Fast Tone Mapping for High Dynamic Range Images", ICPR2004, 17th International Conference on Pattern Recognition, Cambridge, United Kingdom, 23 - 26 August 2004 (PDF)
J. Duan, G. Qiu and G. D. Finlayson,"Learning to display high dynamic range images", CGIV'2004, IS&T's Second European Conference on Color in Graphics, Imaging and Vision,  Aachen, Germany, April 5-8, 2004 (PDF)

Some of our initial results can be found in this page
Copyright © 2005 G Qiu, Last modified September 2005