Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network
Deriving from image matching and understanding, semantic keypoint matching aims at establishing correspondence between keypoint sets in images. As graphs are powerful tools to represent points and their complex relationships, graph matching provides an effective way to find desired semantic keypoint correspondences. Recent deep graph matching methods have shown excellent performance, but there is still a lack of exploration and utilization of spatial information of keypoints as nodes in graphs. More specifically, existing methods are insufficient to capture the relative spatial relations through current graph construction approaches from the locations of semantic keypoints. To address these issues, we introduce a positional reconstruction encoder-decoder (PR-EnDec) to model intrinsic graph spatial structure, and present an end-to-end graph matching network PREGM based on PR-EnDec. Our PR-EnDec consists of a positional encoder that learns effective node spatial embedding with the affine transformation invariance, and a spatial relation decoder that further utilizes the high-order spatial information by reconstructing the locational structure of graphs contained in the node coordinates. Extensive experimental results on three public keypoint matching datasets demonstrate the effectiveness of our proposed PREGM.Submission Number: 4817
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SinAE: A Single-Architecture Flow-Matching Autoencoder for Cross-Domain Atomic Systems
Small molecules, crystals, and proteins all reduce to atoms in 3D space, yet their generative pipelines remain fragmented across domains, each with its Small molecules, crystals, and proteins all reduce to atoms in 3D sp…
LGFCTR: Local and Global Feature Convolutional Transformer for Image Matching
Image matching that finding robust and accurate correspondences across images is a challenging task under extreme conditions. Capturing local and global features simultaneously is an important way to mitigate such an iss…
DecoderregressionSupervised sparse auto-encoders for interpretable and compositional representations
Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scal…
Image EditingSpatial Broadcast Decoder: A Simple Architecture for Disentangled Representations in VAEs
We present a neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. Instead of the deconvolutional network typically used in the decoder of VAEs, we tile (broadcast) …
DecoderNeural RenderingShape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction
We present Shape Non-rigid Kinematics (SNK), a novel zero-shot method for non-rigid shape matching that eliminates the need for extensive training or ground truth data. SNK operates on a single pair of shapes, and employ…
Decoder