Learning Geodesic-aware Local Features From RGB-D Images

Abstract

Most of the existing handcrafted and learning-based local descriptors are still at best approximately invariant to affine image transformations, often disregarding deformable surfaces. In this paper, we take one step further by proposing a new approach to compute descriptors from RGB-D images (where RGB refers to the pixel color brightness and D stands for depth information) that are invariant to isometric non-rigid deformations, as well as to scale changes and rotation. Our proposed description strategies are grounded on the key idea of learning feature representations on undistorted local image patches using surface geodesics. We design two complementary local descriptors strategies to compute geodesic-aware features efficiently: one efficient binary descriptor based on handcrafted binary tests (named GeoBit), and one learning-based descriptor (GeoPatch) with convolutional neural networks (CNNs) to compute features. In different experiments using real and publicly available RGB-D dat

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keypotje2022learning

Related papers

• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• Digging Into Self-supervised Learning Of Feature Descriptors (2021)7.16
• LCD: Learned Cross-domain Descriptors For 2D-3D Matching (2019)13.74
• Enhancing Deformable Local Features By Jointly Learning To Detect And Describe Keypoints (2023)9.59
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Local Gradient Hexa Pattern: A Descriptor For Face Recognition And Retrieval (2022)13.93
• DH3D: Deep Hierarchical 3D Descriptors For Robust Large-scale 6dof Relocalization (2020)14.76
• Location Field Descriptors: Single Image 3D Model Retrieval In The Wild (2019)11.39