We are experiencing a large use of HDR technology in the entertainment sector, and are also starting to see its use in industrial applications. On the other hand, we are assisting in a paradigm change in the image-processing area, where traditional techniques are surpassed by more flexible deep-learning-based approaches. In the last few years, we are also observing this specific trend in the HDR imaging field. This has brought a number of challenges that need to be addressed in order to make deep-learning-based HDR approaches more robust and resilient to unseen data and/or data which is too noisy.
Topics included but not limited to
Deep-learning-based techniques for images/videos for:
High dynamic range (i.e., camera, image and vision, sensors);
Single/multi-exposure HDR content acquisition;
Image fusion for HDR content;
HDR formats and standardization;
HDR objective metrics;
HDR de-ghosting artifacts removal;
Tone mapping/inverse tone mapping;
Color correction for HDR content;
Gamut adjustment for HDR content;
Real-time HDR applications;
Mixed reality for HDR;
Image-based lighting.
