Brightness-enhancement functions (BEFs) generated with our technique using different bilateral-filter algorithms. Input images, and BEFs created using brute force, real-time bilateral filter, bilateral grid, and adaptive manifolds.

High-Quality Reverse Tone Mapping for a Wide Range of Exposures

Rafael Pacheco Kovaleski rpkovaleski@inf.ufrgs.br

Manuel M. Oliveira oliveira@inf.ufrgs.br

Instituto de Informática, UFRGS

Proceedings of SIBGRAPI 2014.
pp. 49-56. [DOI]

Contents

Reverse-tone-mapping operators (rTMOs) enhance low-dynamic-range images and videos for display on high-dynamic-range monitors. A common problem faced by previous rTMOs is the handling of under or overexposed content. Under such conditions, they may not be effective, and even cause loss and reversal of visible contrast. We present an rTMO based on cross-bilateral filtering that generates high-quality HDR images and videos for a wide range of exposures. Experiments performed using an objective image quality metric show that our approach is the only technique available that can gracefully enhance perceived details across a large range of image exposures.

Paper

Full Paper (pre-print)

The final publication is available from IEEE Xplore

Code

MATLAB Code

Full-Resolution Image Results

Image Comparisons

Results of the DRIM metric for the building series of bright/overexposed images. First row: input LDR images. Other rows: DRIM output for the results produced by the rTM operators of Kovaleski and Oliveira [5], Masia and Gutierrez’s [18], and ours. The colors green, blue, and red indicate pixels affected by loss of visible contrast, amplification of invisible contrast, and contrast reversal, respectivel.

Results of the DRIM metric for the graffiti series of bright/overexposed images. First row: input LDR images. Other rows: DRIM output for the results produced by the rTM operators of Kovaleski and Oliveira, Masia and Gutierrez’s, and ours. The colors green, blue, and red indicate pixels affected by loss of visible contrast, amplification of invisible contrast, and contrast reversal, respectively.

Results of the DRIM metric for the car series of dark/underexposed images. First row: input LDR images. Other rows: DRIM output for the results produced by the rTM operators of Kovaleski and Oliveira, Masia and Gutierrez’s, and ours. The colors green, blue, and red indicate pixels affected by loss of visible contrast, amplification of invisible contrast, and contrast reversal, respectively.

Video

Citation

Kovaleski, Rafael and Manuel M. Oliveira "High-Quality Reverse Tone Mapping for a Wide Range of Exposures". Proceedings of SIBGRAPI 2014. pp. 49-56.

BibTeX

@inproceedings{KovaleskiOliveira2014, 
    author={Rafael Kovaleski and Manuel M. Oliveira},
    booktitle={Graphics, Patterns and Images ({SIBGRAPI}), 2014 27th {SIBGRAPI} Conference on}, 
    title={High-Quality Reverse Tone Mapping for a Wide Range of Exposures}, 
    year={2014}, 
    month={Aug}, 
    pages={49-56}, 
    keywords={computer displays;filtering theory;image enhancement;video signal processing;cross-bilateral filtering;high-dynamic-range monitors;high-quality HDR images;high-quality HDR videos;high-quality reverse tone mapping;image exposures;low-dynamic-range image enhancement;low-dynamic-range video enhancement;objective image quality metric;rTMOs;reverse-tone-mapping operators;visible contrast loss;visible contrast reversal;Acceleration;Brightness;Equations;Image edge detection;Measurement;Real-time systems;Videos;cross-bilateral filter;high dynamic range;reverse tone mapping}, 
    doi={10.1109/SIBGRAPI.2014.29}
}

Keywords

Reverse tone mapping, High-dynamic range, Cross-bilateral filtering.

CNPq-Brazil fellowships and grants #308936/2010-8 and 482271/2012-4.