Brown University's PackUV enables 3D volumetric video streaming on existing infrastructure
Brown University researchers have developed PackUV, a new processing method that maps 3D Gaussian Splatting data onto 2D image frames. This innovation allows high-resolution volumetric video to be compressed and streamed using existing codecs and internet infrastructure. The breakthrough enables interactive 3D viewing on standard consumer devices like smartphones and smart TVs, solving previous challenges of storing and streaming terabytes of 3D data.
Key Takeaways
- PackUV maps 3D Gaussian Splatting data onto 2D image frames, enabling volumetric video compression.
- The method allows interactive 3D viewing on standard consumer devices without new display tech.
- PackUV uses existing codecs like those powering Netflix and YouTube for 3D content delivery.
- Brown University's approach can render complex 3D scenes up to 30 minutes in length without breakdown, exceeding other Gaussian Splatting methods.
- Researchers created a publicly available dataset of multi-view video, captured with 50-90 synchronized cameras, to validate the approach.
Why It Matters
This development could significantly lower the barrier to entry for widespread 3D volumetric video in entertainment and other sectors. By converting terabytes of 3D data into streamable 2D formats compatible with existing internet infrastructure, PackUV broadens the potential for interactive content delivery. The streaming industry could see new content formats beyond flat video, enabling immersive experiences and "digital twins" in applications like sports, concerts, or virtual environments. Watch for early adoption by platforms experimenting with interactive or virtual reality content, and further developments in codec optimization for these new formats.
Read full article at thedebrief.org
Get this in your inbox → Subscribe
Enjoy our coverage?
Add StreamingMeme as a preferred source on Google to see more of our streaming news at the top of your Search results.
Add as preferred source