by tylerneylon on 10/14/23, 4:43 AM with 33 comments
by jimmySixDOF on 10/14/23, 10:41 AM
>Gaussian splats are 3d, but currently rendered as 2d cards ordered on centre, not per pixel like they should be.
>So as centres reorder, they "shuffle". This is a showstopper for general adoption in VR
>The solution? Ordering per pixel will solve this, as would stochastic methods which write depth correctly (though those have other problems for VR).
>For it to be viable you need to cull much more aggressively but also can't have any warp divergence when processing samples.
>Unforunately those things are in direct conflict. Paper's renderer is at extreme end of "weak cull, perfect warp convergence".
Apparently need some new Order-Independent Transparency algorithms that handle depth layers.
[1] https://x.com/charshenton/status/1710207169407447396?s=20
by speps on 10/14/23, 9:04 AM
* https://aras-p.info/blog/2023/09/05/Gaussian-Splatting-is-pr...
* https://aras-p.info/blog/2023/09/13/Making-Gaussian-Splats-s...
* https://aras-p.info/blog/2023/09/27/Making-Gaussian-Splats-m...
Gsplat gets a mention:
Aside: the excellent gsplat.tech by Jakub Červený (@jakub_c5y) seems to also be using some sort of VQ/Clustering for the data. Seriously, check it out, it’s probably be nicest gaussian splatting thing right now w.r.t. usability – very intuitive camera controls, nicely presented file sizes, and works on WebGL2. Craftsmanship!
by sprash on 10/14/23, 7:56 AM
by polskibus on 10/14/23, 7:56 AM
by qwertox on 10/14/23, 2:10 PM
https://www.youtube.com/watch?v=kShNYOuDnlI&t=224s
I got it recommended because I watched the following video:
https://www.youtube.com/watch?v=HVv_IQKlafQ&t=64s
Both are worth watching if one didn't know it exists.
by Yenrabbit on 10/14/23, 2:23 PM
by gravypod on 10/14/23, 3:49 PM