Pairingnet: A Learning-based Pair-searching And -matching Network For Image Fragments

Abstract

In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are always difficult to tune hyperparameters for extensive data and computationally time-consuming. Therefore, we propose a neural network that can effectively utilize neighbor textures with contour shape information to fundamentally improve performance. First, we employ a graph-based network to extract the local contour and texture features of fragments. Then, for the pair-searching task, we adopt a linear transformer-based module to integrate these local features and use contrastive loss to encode the global features of each fragment. For the pair-matching task, we design a weighted fusion module to dynamically fuse extracted local contour and texture features, and formulate a similarity matrix for each pair of fragments to calculate the matching score and

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyzhou2023pairingnet

Related papers

• Why And How: Knowledge-guided Learning For Cross-spectral Image Patch Matching (2024)3.31
• Compare More Nuanced:pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning (2019)11.39
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• A New Fine-grained Alignment Method For Image-text Matching (2023)0.00
• Tasks Integrated Networks: Joint Detection And Retrieval For Image Search (2020)11.08
• Optimizing CLIP Models For Image Retrieval With Maintained Joint-embedding Alignment (2024)6.34
• Adapnet: Adaptive Noise-based Network For Low-quality Image Retrieval (2024)0.00
• Improving The Matching Of Deformable Objects By Learning To Detect Keypoints (2023)7.74