Zi-Xin Zou

Mira-Scene is presented, a compositional 3D scene reconstruction framework that replaces sparse pose regression with dense, bounded correspondence recovery and introduces a multimodal diffusion transformer that jointly generates object geometry and CCMs, using modality-specific expert streams with shared attention and positional encoding to promote geometry-layout consistency.

Nexus achieves superior mesh generation by decoupling vertex and topology creation, outperforming traditional methods that struggle with error accumulation.