A geometry-consistent pre-training paradigm using masked inlier reconstruction and a dual-stream encoder produces more robust and generalizable correspondence pruning for camera pose estimation and related 3D tasks.
Megadepth: Learning single-view depth prediction from internet photos
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-training
A geometry-consistent pre-training paradigm using masked inlier reconstruction and a dual-stream encoder produces more robust and generalizable correspondence pruning for camera pose estimation and related 3D tasks.