3R-INN: How to Be Climate Friendly While Consuming/delivering Videos?

Abstract

The consumption of a video requires a considerable amount of energy during the various stages of its life-cycle. With a billion hours of video consumed daily, this contributes significantly to the ghg emission. Therefore, reducing the end-to-end carbon footprint of the video chain, while preserving the quality of experience at the user side, is of high importance. To contribute in an impactful manner, we propose 3R-INN, a single invertible network that does three tasks at once: given a hr grainy image, it Rescales it to a lower resolution, Removes film grain and Reduces its power consumption when displayed. Providing such a minimum viable quality content contributes to reducing the energy consumption during encoding, transmission, decoding and display. 3R-INN also offers the possibility to restore either the hr grainy original image or a grain-free version, thanks to its invertibility and the disentanglement of the high frequency, and without transmitting auxiliary data. Experiments show that, 3R-INN enables significant energy savings for encoding (78%), decoding (77%) and rendering (5% to 20%), while outperforming state-of-the-art film grain removal and synthesis, energy-aware and downscaling methods on different test-sets.