A semi-supervised MVS training method that transfers monocular relative-depth structure priors into MVS predictions via a deep feature loss and a multi-scale statistical loss, improving depth accuracy on ScanNet++ and ARKitScenes.
SceneScript: Reconstructing scenes with an autoregr es- sive structured language model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Prism: Semi-Supervised Multi-View Stereo with Monocular Structure Priors
A semi-supervised MVS training method that transfers monocular relative-depth structure priors into MVS predictions via a deep feature loss and a multi-scale statistical loss, improving depth accuracy on ScanNet++ and ARKitScenes.