Given a query image, Visual Place Recognition (VPR) is the task of retrieving an image of the same place from a reference database with robustness to viewpoint and appearance changes. Recent works show that some VPR benchmarks are solved by methods using Vision-Foundation-Model backbones and trained on large-scale and diverse VPR-specific datasets. Several benchmarks remain challenging, particularly when the test environments differ significantly from the usual VPR training datasets. We propose a complementary, unexplored source of information to bridge the train-test domain gap, which can further improve the performance of State-of-the-Art (SOTA) VPR methods on such challenging benchmarks. Concretely, we identify that the test-time reference set, the "map", contains images and poses of the target domain, and must be available before the test-time query is received in several VPR applications. Therefore, we propose to perform simple Reference-Set-Finetuning (RSF) of VPR models on the map, boosting the SOTA (~2.3% increase on average for Recall@1) on these challenging datasets. Finetuned models retain generalization, and RSF works across diverse test datasets.
Joint Multi-Condition Representation Modelling via Matrix Factorisation for Visual Place Recognition
School of Electronics and Computer Science, University of Southampton（苏塞克斯大学电子与计算机科学学院）；Department of Computer Science and Engineering, Hanyang University（翰阳大学计算机科学与工程系）；QUT Centre for Robotics, School of Electrical Engineering and Robotics（昆士兰大学机器人中心、电气工程与机器人学院）；School of Computer Science and Electronic Engineering, University of Essex（埃塞克斯大学计算机科学与电子工程学院）
RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Baidu Inc.（百度公司）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；School of Future Technology, UCAS（中国科学院大学未来技术学院）；Center for Artificial Intelligence and Robotics, HKISI_CAS（中国科学院香港创新研究院人工智能与机器人创新中心）
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD
Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignment
Department of Electronics and Communications Engineering, Kwangwoon University（韩国 Kwangwoon 大学电子与通信工程系）；Department of Software Engineering, Dankook University（韩国 Dankook 大学软件工程系）；School of Computer Science, University of Birmingham（英国 Birmingham 大学计算机科学学院）
SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models
Southern University of Science and Technology（南方科技大学）；Peng Cheng Laboratory（鹏城实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Cambridge University（剑桥大学）
MRS-VPR: a multi-resolution sampling based global visual place recognition method
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所机器人学国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Biorobotics Lab, Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所生物机器人实验室）
SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition
QUT Centre for Robotics（昆士兰科技大学机器人中心）；School of Electrical Engineering and Robotics, QUT（昆士兰科技大学电气工程与机器人学院）；Queensland University of Technology (QUT)（昆士兰科技大学）
Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization
Dansk Drone Kompagni ApS（丹麦无人机公司）；Technical University of Denmark（丹麦技术大学）；Universidad de Zaragoza（萨拉戈萨大学）
地点识别和视觉定位在宽基线配置中特别具有挑战性。在本文中，我们的贡献与\emph{Danish Airs and Grounds}（DAG）数据集，一个大型的收集街道和航空图像针对这种情况。它的主要挑战在于查询和参考图像之间的极端视角差异，从而改变照明和透视。该数据集比目前公开的数据更大，更多样化，包括城市，郊区和农村地区50多公里的道路。所有图像都与精确的6-DoF元数据相关联，可以对视觉定位方法进行基准测试。我们还提出了一个地图到图像的重新定位管道，首先估计密集的3D重建从航空图像，然后匹配查询街道级图像的3D模型的街道级渲染。数据集可从以下网址下载：https://frederikwarburg.github.io/DAG
