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.

Show replies

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)?

Show replies

This is basically Gaussian splat using cubes instead of Gaussians. The cube centers and sizes choices are discrete and non overlapping, hence the name “sparse voxel”. The qualitative results and rendering speeds are similar to Gaussian splat, and it’s sometimes better or worse depending on the scene.

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.

Show replies

I think this paper is as important as original Gaussian Splatting paper.

Show replies