MVGE: Scale-invariant and Temporal-consistent Monocular Video Geometry Estimation

ICLR 2026 Conference Submission12646 Authors

Keywords: monocular video, 3D geometry, temporal consistency, scale-invariant, point maps, depth estimation, long-range modeling

TL;DR: MVGE achieves both geometric precision and long-range temporal consistency in 3D point map estimation from monocular videos through viewpoint-invariant transformations and frequency-modulated temporal modeling.

Abstract: We present MVGE, 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. Code will be publicly released, and we encourage readers to explore the interactive demonstrations in our supplementary materials.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 12646