Search papers, labs, and topics across Lattice.
Waabi 2 University of Toronto
2
1
4
Forget painstakingly optimizing each urban scene individually: GenRe distills diffusion-based generative priors into 3D Gaussian representations, fixing reconstruction deficiencies in minutes and generalizing to challenging viewpoints.
Vision foundation models can be effectively adapted to significantly improve the detection of rare, safety-critical objects in 3D autonomous driving scenarios, even with limited training data.
