SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry
This work addresses the problem of maintaining geometric accuracy and temporal consistency in 3D reconstruction from long monocular videos, a challenge for existing methods.
SCOPE estimates 3D geometry from extended monocular video sequences, achieving a 24.2% reduction in relative point map error and 34.9% reduction in temporal alignment error on ScanNet compared to state-of-the-art methods.
We present SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry), a novel approach for estimating 3D geometry from extended monocular video sequences, where existing methods struggle to maintain both geometric accuracy and temporal consistency across hundreds of frames. Our approach generates affine-invariant 3D point maps with shared parameters across entire sequences, enabling consistent scale-invariant representations. We introduce three key innovations: viewpoint-invariant geometry aligning multi-perspective points in a unified reference frame; appearance-invariant learning enforcing consistency across exponential timescales; and frequency-modulated positioning enabling extrapolation to sequences vastly exceeding training length. Experiments across diverse datasets demonstrate significant improvements, reducing relative point map error by 24.2% and temporal alignment error by 34.9% on ScanNet compared to state-of-the-art methods. Our approach handles challenging scenarios with complex camera trajectories and lighting variations while efficiently processing extended sequences in a single pass. Project page: https://scope3d.github.io/.