Impressive Video Data Compression

AI Thread Summary
The content discusses advancements in video streaming technology, particularly focusing on data compression techniques that significantly reduce bandwidth requirements. It highlights the blurred lines between algorithms and AI in this context, emphasizing the potential for both innovative applications and the risk of facilitating deep fakes. The technology bears similarities to methods used for animating old photos, where facial points from a recorded actor are mapped to those in static images for video rendering. Additionally, it touches on traditional video compression methods, such as the use of I-frames and P-frames, which optimize data by storing full frames and only the changes between them. Overall, the discussion underscores the dual-edged nature of these advancements in video technology.
anorlunda
Staff Emeritus
Science Advisor
Homework Helper
Insights Author
Messages
11,326
Reaction score
8,750
https://arxiv.org/pdf/2011.15126.pdf
https://nvlabs.github.io/face-vid2vid/
https://wandb.ai/ayush-thakur/face-...hesis-for-Video-Conferencing--Vmlldzo1MzU4ODc

One thing in this modern world seems to be ubiquitous; the demand for streaming more and more video. The
data compression in these papers, appears to be a significant step forward in reducing the bandwidth required.

I don't know whether to call it an algorithm or an AI. The difference is blurry.

On the dark side, it also appears to enable much simpler production of deep fakes.

 
  • Wow
  • Like
Likes Twigg and Borg
Computer science news on Phys.org
Interesting compression. Thanks for sharing.

This seems very similar to the recent animation of old photos using the old photo and a digitized actor doing the actions to be the guide for the video rendering.

They record an actor and key facial points for each frame and then map the old photo facial points to the actors facial points to render the scene.

I imagine too the artifacts can be ignored as side-effects of the video transmission in the viewers mind.

Standard video does something simpler with i-frames and p-frames where the i-frame is a full frame of the image (like jpg or bmp) and the p-frame is what changed.

https://en.wikipedia.org/wiki/Video_compression_picture_types
 
This week, I saw a documentary done by the French called Les sacrifiés de l'IA, which was presented by a Canadian show Enquête. If you understand French I recommend it. Very eye-opening. I found a similar documentary in English called The Human Cost of AI: Data workers in the Global South. There is also an interview with Milagros Miceli (appearing in both documentaries) on Youtube: I also found a powerpoint presentation by the economist Uma Rani (appearing in the French documentary), AI...
Back
Top