Toward Generalized Psychovisual Preprocessing For Video Encoding

iSize News, Technical Articles

A recent issue of the SMPTE Motion Imaging Journal, presents paper entitled Toward Generalized Psychovisual Preprocessing for Video Encoding by Yiannis Andreopoulos, Mohammad Ashraful Anam, Aaron Chadha, Ilya Fadeev, and Matthias Treder. The research explores the use of deep perceptual preprocessing to enable bitrate savings across several generations of video encoders, without breaking standards or requiring any changes in client …

iSIZE BitClear: Making the Unwatchable Watchable

iSize In The Press, News, Technical Articles

Sergio Grce, iSIZE CEO discusses BitClear, an artificial intelligence based denoising technology. Consider the life-cycle of a piece of “viral” media. It might be a rare insight into a news story, an unexpected artistic achievement, or just a funny animal. But it has spread around the media-sharing social sites. Given the quality of cameras available today, even in phones, it …

Pre-encoding 8K with iSIZE BitSave

iSize In The Press, News, Technical Articles

To understand the benefits of pre-encoding 8K content, 8K Association reached out to iSIZE Technologies. iSIZE first uses machine learning to create a psychovisual preprocessor with its BitSave product. This tool can then be deployed in front of any standard codec to provide any combination of lowering bandwidth or increasing video quality. Typically, the model is pre-trained by iSIZE. iSIZE …

iSIZE BitSave high quality video at lower bitrates via Intel DL Boost

iSIZE BitSave: High-quality video at lower bitrates via Intel DL Boost

iSize Technical Articles

This white paper describes iSIZE’s innovative BitSave technology, an AI-based perceptual optimization that adaptively filters the video content before it reaches the codec, such that the output after compressing with any standard video codec is perceptually optimized (e.g., less motion artifacts or blurring), for the same bitrate. Download PDF > 

deep perceptual optimization for video encoding

Deep perceptual optimization for video encoding

iSize Events, Technical Articles

This blog is based on a presentation made by Dr Yiannis Andreopoulos of iSIZE, as part of the Stanford Compression Workshop 2021. The complete presentation can be seen in the video below:   Video now makes up the vast bulk of internet traffic, in terms of bandwidth. Consequently, in the continuing search for efficiency and capacity, there is much interest …