PA-LoFTR: Local Feature Matching with 3D Position-Aware Transformer

Chenhao Li, Qisheng Tang, Shuangjiu Xiao, Ying Mao, Deli Dong, Zhifeng Shi, Guoliang Chen, Jiawen Cheng

Keywords: deep learning, transformer, image matching, pose estimation, position embedding, 3d representation

TL;DR: A Transformer-based method that learns 3D position information to solve image matching problem.

Abstract: We propose a novel image feature matching method that utilizes 3D position information to augment feature representation with a deep neural network. The proposed method introduces 3D position embedding to a state-of-the-art feature matcher, LoFTR, and achieves more promising performance. Following the coarse-to-fine matching pipeline of LoFTR, we construct a Transformer-based neural network that generates dense pixel-wise matches. Instead of using 2D position embeddings for transformer, the proposed method generates 3D position embeddings that can precisely capture position correspondence of matches between images. Importantly, in order to guide neural network to learn 3D space information, we augment features with depth information generated by a depth predictor. In this way, our method, PA-LoFTR, can generate 3D position-aware local feature descriptors with Transformer. We experiment on indoor datasets, and results show that PA-LoFTR improves the performance of feature matching compared to state-of-the-art methods.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)