Since you're here @author :) Do you mind giving a quick rundown on how this competes with the quality of zip-nerf?
SMERF: Streamable Memory Efficient Radiance Fields
61–70 of 152 posts
Re: SMERF: Streamable Memory Efficient Radiance Fields
#62Very impressive demo.
Re: SMERF: Streamable Memory Efficient Radiance Fields
#63Any plans to release the models ?
The pretrained models are already available online! Check out the "demo" section of the website. Your browser is fetching the model when you run the demo.
Re: SMERF: Streamable Memory Efficient Radiance Fields
#64It makes it harder for me to trust the paper if I feel like the paper is trying to persuade me of something rather than describe the complete findings.
Re: SMERF: Streamable Memory Efficient Radiance Fields
#65Im not sure why this demo runs so horribly in Firefox but not other browsers..anyone else having this?
Runs pretty well (20-100 fps depending on the scene) for me on both Firefox 120.1.1 on Android 14 (Pixel 7; smartphone preset) and Firefox 120.0.1 on Fedora 39 (R7 5800, 64 GB memory, RX 6600 XT; 1440p; desktop preset).
WebRender initialization failed Blocklisted; failure code RcANGLE(no compositor device for EGLDisplay)(Create)_FIRST 3D11_COMPOSITING runtime failed Failed to acquire a D3D11 device Blocklisted; failure code FEATURE_FAILURE_D3D11_DEVICE2
I'm running a 3060
Re: SMERF: Streamable Memory Efficient Radiance Fields
#66but perhaps that was biased?
Re: SMERF: Streamable Memory Efficient Radiance Fields
#67Hope this doesn't come as snarky, but does Google pressure researchers to do PR in their papers? This really is cool, but there is a lot of self-promotion in this paper and very little discussion of limitations (and the discussion of them is bookended by qualifications why they really aren't limitations). It makes it harder for me to trust the paper if I feel like the paper is trying to persuade me of something rathe…
Re: SMERF: Streamable Memory Efficient Radiance Fields
#68Re: SMERF: Streamable Memory Efficient Radiance Fields
#69How long until you can stitch Street View into a seamless streaming NeRF of every street in the world? I hope that's the goal you're working towards!
Re: SMERF: Streamable Memory Efficient Radiance Fields
#70Hope this doesn't come as snarky, but does Google pressure researchers to do PR in their papers? This really is cool, but there is a lot of self-promotion in this paper and very little discussion of limitations (and the discussion of them is bookended by qualifications why they really aren't limitations). It makes it harder for me to trust the paper if I feel like the paper is trying to persuade me of something rathe…
People are not allowed to be proud of their work anymore?