Scene-Aware Feature Matching

08/19/2023
by   Xiaoyong Lu, et al.
0

Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when handling challenging scenes such as scenes with large viewpoint and illumination changes. To tackle this problem, we propose a novel model named SAM, which applies attentional grouping to guide Scene-Aware feature Matching. SAM handles multi-level features, i.e., image tokens and group tokens, with attention layers, and groups the image tokens with the proposed token grouping module. Our model can be trained by ground-truth matches only and produce reasonable grouping results. With the sense-aware grouping guidance, SAM is not only more accurate and robust but also more interpretable than conventional feature matching models. Sufficient experiments on various applications, including homography estimation, pose estimation, and image matching, demonstrate that our model achieves state-of-the-art performance.

READ FULL TEXT

page 1

page 3

page 8

research
11/09/2021

Exploiting Robust Unsupervised Video Person Re-identification

Unsupervised video person re-identification (reID) methods usually depen...
research
03/02/2023

ParaFormer: Parallel Attention Transformer for Efficient Feature Matching

Heavy computation is a bottleneck limiting deep-learningbased feature ma...
research
02/18/2022

Guide Local Feature Matching by Overlap Estimation

Local image feature matching under large appearance, viewpoint, and dist...
research
12/20/2021

Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching

Most image matching methods perform poorly when encountering large scale...
research
03/17/2022

MatchFormer: Interleaving Attention in Transformers for Feature Matching

Local feature matching is a computationally intensive task at the subpix...
research
12/05/2019

3D Objectness Estimation via Bottom-up Regret Grouping

3D objectness estimation, namely discovering semantic objects from 3D sc...
research
11/20/2012

Matching Through Features and Features Through Matching

This paper addresses how to construct features for the problem of image ...

Please sign up or login with your details

Forgot password? Click here to reset