MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency
This addresses a specific bottleneck in 3D vision applications where monocular models struggle with consistency across views, offering an incremental improvement.
The paper tackles the problem of cross-view inconsistency and scale ambiguity in monocular 3D foundation models by proposing MoRe, a training-free monocular geometry refinement method that improves 3D reconstruction and novel view synthesis.
Monocular 3D foundation models offer an extensible solution for perception tasks, making them attractive for broader 3D vision applications. In this paper, we propose MoRe, a training-free Monocular Geometry Refinement method designed to improve cross-view consistency and achieve scale alignment. To induce inter-frame relationships, our method employs feature matching between frames to establish correspondences. Rather than applying simple least squares optimization on these matched points, we formulate a graph-based optimization framework that performs local planar approximation using the estimated 3D points and surface normals estimated by monocular foundation models. This formulation addresses the scale ambiguity inherent in monocular geometric priors while preserving the underlying 3D structure. We further demonstrate that MoRe not only enhances 3D reconstruction but also improves novel view synthesis, particularly in sparse view rendering scenarios.