"FSTM - Replica Set"

"This collection is part of a paper called \"First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction\" or FSTM in short.FSTM, is a unified approach for learning geometry and semantics through a two-step process: a geometry warm-up using RGB inputs and geometric cues, followed by semantic field estimation.By first optimising geometry without semantic supervision, we observe substantial improvements compared to the standard joint optimisation.Rather than relying on specialised modules or complex multi-SDF designs, FSTM shows that a streamlined formulation is sufficient to achieve strong geometric and semantic reconstructions.We provide the meshes generated by out method for the Replica set of 8 scenes. Each scene has both the scene- and object-level meshes."