Yujiao Shi

Panoramic 3D reconstruction gets a boost with PanoVGGT, a Transformer that handles spherical distortions and global-frame ambiguity to deliver state-of-the-art accuracy in a single pass.

Diffusion models can now generate more realistic and semantically appropriate hand grasps by explicitly modeling affordances and interaction semantics, outperforming prior methods on grasp quality, semantic accuracy, and diversity.