Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
TLDR
This work proposes effective tone mapping and inverse tone mapping algorithms for production, post-production and exhibition and believes 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.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.read more
Citations
More filters
Digital Video And Hdtv Algorithms And Interfaces
TL;DR: The digital video and hdtv algorithms and interfaces is universally compatible with any devices to read and is available in the book collection an online access to it is set as public so you can get it instantly.
Journal Article
Synaptic rectification controls nonlinear spatial integration of natural visual inputs
Maxwell H. Turner,Fred Rieke +1 more
TL;DR: It is demonstrated that nonlinear spatial integration, a common feature of retinal ganglion cell (RGC) processing, shapes neural responses to natural visual stimuli in primate Off parasol RGCs, whereas On parasolRGCs exhibit surprisingly linear spatial integration.
Journal ArticleDOI
Photorealistic style transfer for video
TL;DR: An efficient example-based photorealistic style transfer algorithm for video that outperforms diverse state-of-the-art methods according to observer preference experiments, bringing savings in pre-production, shooting and post-production time.
Journal ArticleDOI
Image Quality Evaluation in Professional HDR/WCG Production Questions the Need for HDR Metrics
TL;DR: In this article , the authors show that the performance of HDR metrics is worse than that of a classic, simple standard dynamic range (SDR) metric applied directly to the HDR content, and that the chrominance metrics specifically developed for HDR/WCG imaging have poor correlation with observer scores.
Proceedings ArticleDOI
Analysis of high dynamic range light field images in practical utilization contexts
TL;DR: A context-dependent analysis of HDR light field imaging that takes into consideration global illumination and rendering challenges, and provides a set of recommendations regarding the use-case-specific requirements of the investigated practical contexts.
References
More filters
Posted Content
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
TL;DR: A new dataset of human perceptual similarity judgments is introduced and it is found that deep features outperform all previous metrics by large margins on this dataset, and suggests that perceptual similarity is an emergent property shared across deep visual representations.
Proceedings ArticleDOI
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
TL;DR: In this paper, the authors introduce a new dataset of human perceptual similarity judgments, and systematically evaluate deep features across different architectures and tasks and compare them with classic metrics, finding that deep features outperform all previous metrics by large margins on their dataset.
Book
High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting
TL;DR: The Human Visual System and HDR Tone Mapping and Frequency Domain and Gradient Domain Tone Reproduction and an Image-Based Lighting List of Symbols References Index are presented.
Book
Eye, brain, and vision
TL;DR: The author describes how the visual circuits develop before birth and the unexpected consequences of visual deprivation early in life, and describes current knowledge concerning the higher visual areas of the brain known as 18, V4 and MT.
Journal ArticleDOI
Parallel processing in the mammalian retina.
TL;DR: The authors' eyes send different 'images' of the outside world to the brain — an image of contours (line drawing), a colour image (watercolour painting) or a image of moving objects (movie) — and circuits that involve complex inhibitory and excitatory interactions represent filters that select 'what the eye tells the brain'.
Related Papers (5)
Common Limitations of Image Processing Metrics: A Picture Story
Annika Reinke,Matthias Eisenmann,Minu D. Tizabi,Carole H. Sudre,Tim Rädsch,Michela Antonelli,Tal Arbel,Spyridon Bakas,M. Jorge Cardoso,Veronika Cheplygina,Keyvan Farahani,Ben Glocker,Doreen Heckmann-Nötzel,Fabian Isensee,Pierre Jannin,Charles E. Kahn,Jens Kleesiek,Tahsin Kurc,Michal Kozubek,Bennett A. Landman,Geert Litjens,Klaus H. Maier-Hein,Bjoern H. Menze,Henning Müller,Jens Petersen,Mauricio Reyes,Nicola Rieke,Bram Stieltjes,Ronald M. Summers,Sotirios A. Tsaftaris,Bram van Ginneken,Annette Kopp-Schneider,Paul F. Jäger,Lena Maier-Hein +33 more