FSTM improves indoor reconstruction by training geometry first without semantic supervision, then adding semantics, achieving 2.3x faster training and higher object surface recall than joint optimization.
H2o-sdf: two-phase learning for 3d indoor reconstruction us- ing object surface fields
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction
FSTM improves indoor reconstruction by training geometry first without semantic supervision, then adding semantics, achieving 2.3x faster training and higher object surface recall than joint optimization.