Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Given a set of images, output local and global pointmaps + confidences for each image. Can recover cameras later using PnP.

Architecture

Dust3r inspired (Croco ViT encoder)

Index embedding

Draw \(N \ll N', N' \approx 10^{3}, N \approx 20\) indices at random during training. This allows scaling to \(N'\) views during inference.

Performance