HKUST-SAIL/SAIL-Recon · Apply for community grant: Academic project (gpu)

HKUST Spatial Artificial Intelligence Lab org 5 days ago

SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization
Sail-Recon is a feed-forward Transformer that scales neural scene regression to large-scale Structure-from-Motion by augmenting it with visual localization. From a few anchor views, it constructs a global latent scene representation that encodes both geometry and appearance. Conditioned on this representation, the network directly regresses camera poses, intrinsics, depth maps, and scene coordinate maps for thousands of images in minutes, enabling precise and robust reconstruction without iterative optimization.

hysts

5 days ago

Hi @poptree , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.
If you can, we ask that you upgrade to Enterprise to enjoy higher ZeroGPU quota and other features like Dev Mode, Private Storage, and more: hf.co/enterprise

ysharma

4 days ago

Hi @poptree , congratulations on your incredible release and the zeroGPU grant! It would be fantastic if you could add a couple of examples to the UI—I'm sure it would make everything even more helpful and welcoming. Great job and looking forward to seeing your next steps!