SOURCE-LINKED INTELLIGENCE

On-the-Fly3R: Towards Robust Online 3D Reconstruction with Feed-Forward 3R Models for Large-Scale UAV Scenarios

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

While feed-forward 3D reconstruction (3R) offers efficient end-to-end modeling, its application in large-scale UAV mapping is hindered by the prohibitive memory cost of Transformer attention. Current scalable streaming 3R methods assume temporally and spatially continuous inputs, rendering them ineffective for the weakly ordered or unordered image streams common in cross-strip UAV operations. To address this, we propose On-the-Fly3R, a training-free, progressive online 3D reconstruction framework for large-scale UAV images that upgrades various 3R backbones for large-scale UAV scenarios. Our m

Read original source ↗ Open in workspace

recordType

paper

region

Global