Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

2026-07-20

AI Summary

Existing monocular geometry estimation methods, constrained by 2D image-space modeling, struggle to recover fine-grained 3D structures such as thin objects and small targets, often resulting in local distortions and excessive smoothing. This work proposes a Self-supervised Sparse Voxel Refinement (SSR) mechanism that elevates geometric modeling into 3D space: starting from a coarse point map generated by a base model, it initializes sparse voxels and employs sparse 3D convolutions to aggregate features within true 3D neighborhoods, iteratively refining geometric details through a self-guided strategy. SSR introduces, for the first time, a self-guided sparse 3D voxel representation that achieves high-fidelity, metric-scale reconstruction while maintaining computational efficiency. Experiments demonstrate significant performance gains over state-of-the-art methods across multiple datasets, with both quantitative metrics and visual results confirming its superior ability to recover complex geometric structures.

Abstract

Monocular geometry estimation has recently achieved impressive performance across diverse scenes. However, state-of-the-art models still face notable distortion in local 3D structure, especially in fine details, like thin structures and small objects. We attribute this limitation to an architectural mismatch: most current models decode 3D geometry within a 2D parameterization, where feature interactions are governed by image-plane proximity rather than true 3D spatial relationships. This inadvertently mixes features from geometrically distant surfaces, resulting in over-smoothed geometry particularly around thin or elongated structure. In this paper, we propose a fine-detail monocular geometry estimation with Self-Guided Sparse 3D Refinement (SSR) that lifts monocular geometry modeling from 2D image space to 3D space for high-fidelity metric-scale point maps. Our model lifts the coarse point map from a foundation base model onto a sparse voxel shell and refines it via SSR. The SSR employs sparse convolutions that aggregate features based on 3D spatial locality, avoiding feature mixing across depth discontinuities. Extensive experiments on diverse datasets demonstrate that our method significantly outperforms existing approaches in recovering fine detailed 3D geometry across both quantitative metrics and qualitative visualizations.

Problem

• monocular geometry estimation
• fine-detail reconstruction
• 3D structure distortion
• thin structures
• depth discontinuities

Innovation

• monocular geometry estimation
• sparse volumetric refinement
• 3D spatial locality
• self-guided refinement
• fine-detail reconstruction