LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding

LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding explores A novel framework for open-vocabulary 3D scene understanding that uses sparse voxel rasterization and foundation models to overcome spatial and semantic ambiguities, achieving state-of-the-art performance.. Commercial viability score: 7/10 in 3D Scene Understanding.