Spann3R uses a learned spatial memory to regress per-image pointmaps directly in a shared global coordinate system, removing the need for optimization-based alignment after per-pair predictions.
A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation
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
-
3D Reconstruction with Spatial Memory
Spann3R uses a learned spatial memory to regress per-image pointmaps directly in a shared global coordinate system, removing the need for optimization-based alignment after per-pair predictions.