GREATEN fuses surface normals with image features via gated contextual-geometric fusion and efficient sparse attentions to cut stereo matching errors by up to 30% on real datasets when trained solely on synthetic data.
Monster++: Unified stereo matching, multi- view stereo, and real-time stereo with monodepth priors
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
-
Geometry Reinforced Efficient Attention Tuning Equipped with Normals for Robust Stereo Matching
GREATEN fuses surface normals with image features via gated contextual-geometric fusion and efficient sparse attentions to cut stereo matching errors by up to 30% on real datasets when trained solely on synthetic data.