Search papers, labs, and topics across Lattice.
4
0
6
Achieve flicker-free, scalable reconstruction of long dynamic videos by blending the best of stream and clip-based Gaussian Splatting.
Synthesizing geometrically plausible rear views from a single image is now possible, thanks to a novel approach that leverages 3D foundation priors to guide video generation.
Current multimodal LLMs struggle with guideline-constrained clinical reasoning, but a simple multi-agent framework can significantly boost their performance on real-world lung cancer diagnosis and treatment.
Stop generating floating shadows and inconsistent illumination: LGI maps leverage monocular depth to capture light-geometry interactions, enabling physically consistent shadow generation and relighting.
