A single-pass transformer generalizes DUSt3R's pointmap regression from two views to all-to-all multi-view attention, reconstructing 1000+ images and estimating camera poses in one forward pass.
Neural rgb-d surface reconstruction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
A single-pass transformer generalizes DUSt3R's pointmap regression from two views to all-to-all multi-view attention, reconstructing 1000+ images and estimating camera poses in one forward pass.