Convolutional neural network architecture for geometric matching

Abstract

We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters. The contributions of this work are three-fold. First, we propose a convolutional neural network architecture for geometric matching. The architecture is based on three main components that mimic the standard steps of feature extraction, matching and simultaneous inlier detection and model parameter estimation, while being trainable end-to-end. Second, we demonstrate that the network parameters can be trained from synthetically generated imagery without the need for manual annotation and that our matching layer significantly increases generalization capabilities to never seen before images. Finally, we show that the same model can perform both instance-level and category-level matching giving state-of-the-art results on the challenging Proposal Flow dataset.

In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)

References in corpus (1)

• Learning to Compare Image Patches via Convolutional Neural Networks

Cited by in corpus (20)

• Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation
• Self-Improving Visual Odometry
• Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera
• Unsupervised learning of object frames by dense equivariant image labelling
• Toward Characteristic-Preserving Image-based Virtual Try-On Network
• Unsupervised Learning of 3D Point Set Registration
• CATs: Cost Aggregation Transformers for Visual Correspondence
• MotionSqueeze: Neural Motion Feature Learning for Video Understanding
• Feature Robust Optimal Transport for High-dimensional Data
• Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds
• Joint Learning of Semantic Alignment and Object Landmark Detection
• VideoMatch: Matching based Video Object Segmentation
• Semantic Attribute Matching Networks
• Statistical transformer networks: learning shape and appearance models via self supervision
• DGC-Net: Dense Geometric Correspondence Network
• PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
• Align-and-Attend Network for Globally and Locally Coherent Video Inpainting
• Learning-based Natural Geometric Matching with Homography Prior
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency
• Learning to Align Images using Weak Geometric Supervision