_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
URI Visit Hacker News on the Web
COMMENT PAGE FOR:
URI Sparse Voxels Rasterization: Real-Time High-Fidelity Radiance Field Rendering
markisus wrote 3 hours 38 min ago:
This is basically Gaussian splat using cubes instead of Gaussians. The
cube centers and sizes choices are discrete and non overlapping, hence
the name âsparse voxelâ. The qualitative results and rendering
speeds are similar to Gaussian splat, and itâs sometimes better or
worse depending on the scene.
HexDecOctBin wrote 9 hours 32 min ago:
Why is this called rendering, when it would be more accurate to call it
reverse-rendering (unless "rendering" means any kind of transformation
of visual-adjacent data)?
yorwba wrote 7 hours 50 min ago:
The reverse-rendering is not real-time, but takes several minutes.
Only rendering new viewpoints from the resulting sparse voxel
representation runs at high enough framerates.
bondarchuk wrote 15 hours 23 min ago:
Funny, it almost sounds like a straight efficiency improvement of
Plenoxels (the direct predecessor of gaussian splatting), which would
mean gaussian splatting was something of a a red herring/sidetrack.
Though I'm not sure atm where the great performance gain is. Definitely
interesting.
ibrarmalik wrote 11 hours 43 min ago:
How is plenoxels a direct predecessor of gaussian splatting?
yyeboah wrote 8 hours 49 min ago:
They both emerged out of the pursuit of a more efficient solution
for addressing the inefficiencies in NeRF, which was mainly due to
expensive ray marching and MLP calls. Before the emergence of
Gaussian splatting, grids, such as plenoxels were all the rage. Of
course, Gaussian splatting here refers to the paper, â3D Gaussian
Splatting for Real-Time Radiance Field Renderingâ
loxias wrote 16 hours 56 min ago:
I look forward to reading this in closer detail, but it looks like they
solve an inverse problem to recover a ground truth set of voxels (from
a large set of 2d images with known camera parameters), which is
underconstrained. Neat to me that it works w/o using dense optical
flow to recover the structure -- I wouldn't have thought that would
converge.
Love this a whole heck of a lot more than NeRF, or any other "lol lets
just throw a huge network at it" approach.
bondarchuk wrote 15 hours 40 min ago:
>Love this a whole heck of a lot more than NeRF, or any other "lol
lets just throw a huge network at it" approach.
Well yes, but that's what gaussian splatting also was. The question
is: are their claims to be so much better than gsplat accurate?
chpatrick wrote 15 hours 25 min ago:
There's no neural net with gaussian splatting, it's a fancy
pointcloud that's optimized with ML techniques.
bondarchuk wrote 15 hours 16 min ago:
I know, that's the point.
chpatrick wrote 15 hours 0 min ago:
Mea culpa, I misunderstood.
davikr wrote 17 hours 23 min ago:
What is the usecase for radiance fields?
corysama wrote 16 hours 0 min ago:
Take a bunch of photos of an object or scene. Fly around the scene
inside a computer. [1] Like photogrammetry. But, handles a much wider
range of materials.
URI [1]: https://news.ycombinator.com/item?id=43120582
aaroninsf wrote 17 hours 38 min ago:
Can someone ELI5 what the input to these renders is?
I'm familiar with the premise of NeRF "grab a bunch of relatively low
resolution images by walking in a circle around a subject/moving
through a space", and then rendering novel view points,
but on the landing page here the videos are very impressive (though the
volumetric fog in the classical building is entertaining as a corner
case!),
but I have no idea what the input is.
I assume if you work in this domain it's understood,
"oh these are all standard comparitive output, source from , which if
you must know are a series of N still images taken... " or
"...excerpted image from consumer camera video while moving through the
space" and N is understood to be 1, or more likely, 10, or 100...
...but what I want to know is,
are these video- or still-image input;
and how much/many?
vessenes wrote 17 hours 0 min ago:
They are photos, in this case from the MIP Nerf 360 dataset. I
believe there are on the order of hundreds per scene. They are not
videos turned into photos. Some datasets include high grade position
and directional information -- I believe this dataset does not, so
you need to do some work to orient the rendering training. But, I'm a
hobbyist, so all this could be very wrong.
corysama wrote 17 hours 29 min ago:
> We optimize adaptive sparse voxels radiance field from multi-view
imagesâ¦
Pretty sure the input is the same as for NeRFS, GS and
photogrammetry: as many high rez photos from as many angles as you
have the patience to collect.
I think the example scenes are from a common collection of photos
that are being widely used as a common reference point.
atilimcetin wrote 17 hours 41 min ago:
I think this paper is as important as original Gaussian Splatting
paper.
mitthrowaway2 wrote 16 hours 42 min ago:
Why do you say so?
DIR <- back to front page