Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images
This work addresses a bottleneck in geometric estimation from images for computer vision applications, though it appears incremental as it builds on existing depth and normal estimation frameworks.
The paper tackles the problem of accurately estimating depth and surface normal from monocular images by addressing the bottleneck of unreliable geometric context capture in existing methods, resulting in a novel Adaptive Surface Normal constraint that improves 3D geometry quality and outperforms state-of-the-art methods on diverse datasets.
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric context in existing methods impedes their ability to accurately enforce the consistency between the different geometric properties, thereby leading to a bottleneck of geometric estimation quality. We therefore propose the Adaptive Surface Normal (ASN) constraint, a simple yet efficient method. Our approach extracts geometric context that encodes the geometric variations present in the input image and correlates depth estimation with geometric constraints. By dynamically determining reliable local geometry from randomly sampled candidates, we establish a surface normal constraint, where the validity of these candidates is evaluated using the geometric context. Furthermore, our normal estimation leverages the geometric context to prioritize regions that exhibit significant geometric variations, which makes the predicted normals accurately capture intricate and detailed geometric information. Through the integration of geometric context, our method unifies depth and surface normal estimations within a cohesive framework, which enables the generation of high-quality 3D geometry from images. We validate the superiority of our approach over state-of-the-art methods through extensive evaluations and comparisons on diverse indoor and outdoor datasets, showcasing its efficiency and robustness.