This is __really__ stunning work, huge, huge, deal that I'm seeing this in a web browser on my phone. Congratulations!
When I look at the NYC scene in the highest quality on desktop, I'm surprised by how low-quality ex. the stuff on the counter and shelves is. So then I load the lego model, and see that's _very_ detailed, so it doesn't seem inherent to the method.
Is it a consequence of input photo quality, or something else?
> Is it a consequence of input photo quality, or something else?
It's more a consequence of spatial resolution: the bigger the space, the more voxels you need to maintain a fixed resolution (e.g. 1 mm^3). At some point, we have to give up spatial resolution to represent larger scenes.
A second limitation is the teacher model we're distilling. Zip-NeRF (https://jonbarron.info/zipnerf/) is good, but it's not _perfect_. SMERF reconstruction quality is upper-bounded by its Zip-NeRF teacher.
When I look at the NYC scene in the highest quality on desktop, I'm surprised by how low-quality ex. the stuff on the counter and shelves is. So then I load the lego model, and see that's _very_ detailed, so it doesn't seem inherent to the method.
Is it a consequence of input photo quality, or something else?