Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
- PDF / 2,766,076 Bytes
- 27 Pages / 439.642 x 666.49 pts Page_size
- 68 Downloads / 148 Views
Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies Praveen Cyriac1 · Trevor Canham1 · David Kane1 · Marcelo Bertalm´ıo1 Received: 30 September 2019 / Revised: 29 June 2020 / Accepted: 4 August 2020 / © The Author(s) 2020
Abstract Many challenges that deal with processing of HDR material remain very much open for the film industry, whose extremely demanding quality standards are not met by existing automatic methods. Therefore, when dealing with HDR content, substantial work by very skilled technicians has to be carried out at every step of the movie production chain. Based on recent findings and models from vision science, we propose in this work effective tone mapping and inverse tone mapping algorithms for production, post-production and exhibition. These methods are automatic and real-time, and they have been both fine-tuned and validated by cinema professionals, with psychophysical tests demonstrating that the proposed algorithms outperform both the academic and industrial state-of-the-art. We believe these methods bring the field closer to having fully automated solutions for important challenges for the cinema industry that are currently solved manually or sub-optimally. Another contribution of our research is to highlight the limitations of existing image quality metrics when applied to the tone mapping problem, as none of them, including two state-of-the-art deep learning metrics for image perception, are able to predict the preferences of the observers. Keywords High dynamic range · Vision models · Visual perception · Tone mapping · Inverse tone mapping · Cinema post-production
1 Introduction High Dynamic Range (HDR) technology can provide a never before seen increase in contrast, colour and luminance. The stunning appearance that HDR images can have has led the industry to see HDR technology as the next generation of video content and is expected to deliver a transforming user experience, representing for some “the most exciting format to come along since color TV” [22]. The contribution of HDR to the sense of immersion stems from the fact that HDR images appear much more faithful to an actual perceived scene, allowing the viewer to resolve details in quite dark or quite bright regions, to distinguish Marcelo Bertalm´ıo
[email protected] 1
Universitat Pompeu Fabra, Barcelona, Spain
Multimedia Tools and Applications
subtle colour gradations, to perceive highlights as much brighter than diffuse white surfaces, all things that we associate with everyday experiences and that cannot be reproduced using SDR (Standard Dynamic Range) systems. This also allows filmmakers to overcome artistic limitations that have existed since the inception of cinema, giving them the “perceptual tools that fine artists working in the medium of painting have had for hundreds of years” [77] and that provide compelling new opportunities for storytelling. Besides the enthusiasm about the unparalleled improvement in picture quality for new content, the industry expects, through re-
Data Loading...
