SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms
Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural networks has been on the rise recently. Rotation-equivariance and scale-equivariance are both critical in correspondence matching applications. Classical correspondence matching approaches are designed to withstand scaling and rotation transformations. However, the features extracted using convolutional neural networks (CNNs) are only translation-equivariant to a certain extent. Recently, researchers have strived to improve the rotation-equivariance of CNNs based on group theories. Sim(2) is the group of similarity transformations in the 2D plane. This paper presents a specialized dataset dedicated to evaluating sim(2)-equivariant correspondence matching algorithms. We compare the performance of 16 state-of-the-art (SoTA) correspondence matching approaches. The experimental results demonstrate the importance of group equivariant algorithms for correspondence matching on various sim(2) transformation conditions. Since the subpixel accuracy achieved by CNN-based correspondence matching approaches is unsatisfactory, this specific area requires more attention in future works. Our dataset is publicly available at: mias.group/SIM2E.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingSimilar Papers 제목 키워드 기반
Learning Rotation-Equivariant Features for Visual Correspondence
Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to ext…
Camera Pose EstimationPose EstimationSelf-Supervised LearningRigid Single-Slice-in-Volume registration via rotation-equivariant 2D/3D feature matching
2D to 3D registration is essential in tasks such as diagnosis, surgical navigation, environmental understanding, navigation in robotics, autonomous systems, or augmented reality. In medical imaging, the aim is often to p…
3D Feature MatchingLearning Probabilistic Symmetrization for Architecture Agnostic Equivariance
We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. In contrary to equivariant architectures, we use an arbitrary base model such as an MLP o…
Graph ClassificationGraph RegressionLink PredictionRobust Noisy Correspondence Learning with Equivariant Similarity Consistency
The surge in multi-modal data has propelled cross-modal matching to the forefront of research interest. However the challenge lies in the laborious and expensive process of curating a large and accurately matched mul…
TripletGLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras
We propose, implement, and compare with competitors a new architecture of equivariant neural networks based on geometric (Clifford) algebras: Generalized Lipschitz Group Equivariant Neural Networks (GLGENN). These networ…
Benchmarking