Search papers, labs, and topics across Lattice.
The Hong Kong University of Science and Technology
4
0
5
4
WAT3R achieves high-quality underwater 3D reconstruction by effectively adapting to imaging degradation in a single forward pass, outperforming existing methods.
Injecting 6D Plucker coordinates into video transformers can drastically improve 3D consistency and camera control in generated videos.
Reliably erase broad concepts like "sexual" or "violent" from diffusion models by using learned concept prototypes as negative guidance, outperforming existing methods.
Unlock real-time, holistic 3D tracking of every pixel in a video with Track4World, a feedforward model that leapfrogs past slow, optimization-based methods.