Inside Out Visual Place Recognition

Abstract: Visual Place Recognition (VPR) is generally concerned with localizing outdoor images. However, localizing indoor scenes that contain part of an outdoor scene can be of large value for a wide range of applications. In this paper, we introduce Inside Out Visual Place Recognition (IOVPR), a task aiming to localize images based on outdoor scenes visible through windows. For this task we present the new large-scale dataset Amsterdam-XXXL, with images taken in Amsterdam, that consists of 6.4 million panoramic street-view images and 1000 user-generated indoor queries. Additionally, we introduce a new training protocol Inside Out Data Augmentation to adapt Visual Place Recognition methods for localizing indoor images, demonstrating the potential of Inside Out Visual Place Recognition. We empirically show the benefits of our proposed data augmentation scheme on a smaller scale, whilst demonstrating the difficulty of this large-scale dataset for existing methods. With this new task we aim to encourage development of methods for IOVPR. The dataset and code are available for research purposes at https://github.com/saibr/IOVPR.

Inside Out Visual Place Recognition

Sarah Ibrahimi, Nanne van Noord, Tim Alpherts, Marcel Worring

Comments

Similar Papers

Modality-Agnostic Topology Aware Localization

Farhad G. Zanjani, Ilia Karmanov, Hanno Ackermann and Daniel Dijkman, Simone Merlin, Max Welling, Fatih Porikli

Keywords Abstract Paper

optimal transport

POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments

Yiming Wang, Francesco Giuliari, Riccardo Berra and Alberto Castellini, Alessio Del Bue, Alessandro Farinelli, Marco Cristani, Francesco Setti

Keywords Abstract Paper

Object Recognition Active Visual Search Partially Observable Markov Decision Process Monte Carlo Tree Search

NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset

Igor Morawski, Yu-An Chen, Yu-Sheng Lin, Winston H. Hsu

Keywords Abstract Paper

low-light, dataset, poor visibility, object detection, image enhancement, adverse, dark, night

A Foundation for 3D Human Behavior Detection in Privacy-Sensitive Domains

Thomas TH Heitzinger, Martin Kampel

Keywords Abstract Paper

3d human behavior analysis, privacy preserving machine learning, multimodal data, depth imaging, thermal imaging, 3d object detection, tracking

Awareness, Understanding, and Action: A Conceptual Framework of User Experiences and Expectations about Indoor Air Quality Visualizations

Sunyoung Kim, Muyang Li

Keywords Abstract Paper

indoor air quality, peripheral display, design principles

Embodied Visual Active Learning for Semantic Segmentation

David Nilsson, Aleksis Pirinen, Erik Gärtner, Cristian Sminchisescu

Keywords Abstract Paper

Multimodal text style transfer for outdoor vision-and-language navigation

Wanrong Zhu, Xin Wang, Tsu-Jui Fu and An Yan, Pradyumna Narayana, Kazoo Sone, Sugato Basu, William Yang Wang

Keywords Abstract Paper

Supervised Training of Dense Object Nets using Optimal Descriptors for Industrial Robotic Applications

Andras Gabor Kupcsik, Markus Spies, Alexander Klein and Marco Todescato, Nicolai Waniek, Philipp Schillinger, Mathias Bürger

Keywords Abstract Paper

Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image

Yinyu Nie, Xiaoguang Han, Shihui Guo and Yujian Zheng, Jian Chang, Jian Jun Zhang

Keywords Abstract Paper

scene understanding, single-view reconstruction, 3d deep learning

Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation

Guoliang Kang, Yunchao Wei, Yi Yang and Yueting Zhuang, Alexander Hauptmann

Keywords Abstract Paper

Cars Can’t Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention Networks

Sungha Choi, Joanne T. Kim, Jaegul Choo

Keywords Abstract Paper

segmentation, autonomous driving, attention networks, automotive, cityscapes, semantic segmentation

Anchor-free Small-scale Multispectral Pedestrian Detection

Alexander Wolpert, Michael Teutsch, Saquib Sarfraz, Rainer Stiefelhagen

Keywords Abstract Paper

pedestrian detection, human recognition, multi-modal, thermal infrared, multispectral fusion, low object resolution, multispectral data augmentation, box-less object detection

Seeing Through Your Skin: Recognizing Objects With a Novel Visuotactile Sensor

Francois R. Hogan, Michael Jenkin, Sahand Rezaei-Shoshtari and Yogesh Girdhar, David Meger, Gregory Dudek

Keywords Abstract Paper

Engaging with Public Art: An Exploration of the Design Space

Tim Gorichanaz

Keywords Abstract Paper

design probe, public art, moral learning, reflection

Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks

Mostafa S. Ibrahim, Arash Vahdat, Mani Ranjbar, William G. Macready

Keywords Abstract Paper

semi-supervised semantic segmentation, ancillary model, self-correction net, noisy labels

Centroid Based Concept Learning for RGB-D Indoor Scene Classification

Ali Ayub, Alan Wagner

Keywords Abstract Paper

cognitively-inspired learning, RGBD analysis, scene classification, category merging, labeling flaws analysis

Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery

Lei Jin, Yanyu Xu, Jia Zheng and Junfei Zhang, Rui Tang, Shugong Xu, Jingyi Yu, Shenghua Gao

Keywords Abstract Paper

depth estimation, 360 indoor imagery, geometric structure, with and without furniture

Learning Affordance Landscapes for Interaction Exploration in 3D Environments

Tushar Nagarajan, Kristen Grauman

Keywords Abstract Paper

Algorithms -> Multitask and Transfer Learning; Algorithms -> Online Learning, Deep Learning

ATISS: Autoregressive Transformers for Indoor Scene Synthesis

Despoina Paschalidou, Amlan Kar, Maria Shugrina and Karsten Kreis, Andreas Geiger, Sanja Fidler

Keywords Abstract Paper

transformers, generative model

Computation Reallocation for Object Detection

Feng Liang, Chen Lin, Ronghao Guo and Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang

Keywords Abstract Paper

Neural Architecture Search, Object Detection

Move to See Better: Self-Improving Embodied Object Detection

Farhad G. Zanjani, Ilia Karmanov, Hanno Ackermann and
Daniel Dijkman, Simone Merlin, Max Welling, Fatih Porikli

Keywords Paper

Yiming Wang, Francesco Giuliari, Riccardo Berra and
Alberto Castellini, Alessio Del Bue, Alessandro Farinelli, Marco Cristani, Francesco Setti

Keywords Paper

Keywords Paper

Keywords Paper

Keywords Paper

Keywords Paper

Wanrong Zhu, Xin Wang, Tsu-Jui Fu and
An Yan, Pradyumna Narayana, Kazoo Sone, Sugato Basu, William Yang Wang

Keywords Paper

Andras Gabor Kupcsik, Markus Spies, Alexander Klein and
Marco Todescato, Nicolai Waniek, Philipp Schillinger, Mathias Bürger

Keywords Paper

Yinyu Nie, Xiaoguang Han, Shihui Guo and
Yujian Zheng, Jian Chang, Jian Jun Zhang

Keywords Paper

Guoliang Kang, Yunchao Wei, Yi Yang and
Yueting Zhuang, Alexander Hauptmann

Keywords Paper

Keywords Paper

Keywords Paper

Francois R. Hogan, Michael Jenkin, Sahand Rezaei-Shoshtari and
Yogesh Girdhar, David Meger, Gregory Dudek

Keywords Paper

Keywords Paper

Keywords Paper

Keywords Paper

Lei Jin, Yanyu Xu, Jia Zheng and
Junfei Zhang, Rui Tang, Shugong Xu, Jingyi Yu, Shenghua Gao

Keywords Paper

Keywords Paper

Despoina Paschalidou, Amlan Kar, Maria Shugrina and
Karsten Kreis, Andreas Geiger, Sanja Fidler

Keywords Paper

Feng Liang, Chen Lin, Ronghao Guo and
Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang

Keywords Paper

Zhaoyuan Fang, Ayush Jain, Gabriel Sarch and
Adam Harley, Katerina Fragkiadaki

Keywords Paper

Keywords Paper

Keywords Paper

Mingxuan Yue, Tianshu Sun, Fan Wu and
Lixia Wu, Yinghui Xu, Cyrus Shahabi

Keywords Paper

Keywords Paper

Keywords Paper

Keywords Paper

Michael Nebeling, Maximilian Speicher, Xizi Wang and
Shwetha Rajaram, Brian Hall, Zijian Xie, Alexander Raistrick, Michelle Aebersold, Edward Happ, Jiayin Wang, Yanan Sun, Lotus Zhang, Leah Ramsier, Rhea Kulkarni

Keywords Paper

Bin Yuan, Yan Jia, Luyi Xing and
Dongfang Zhao, XiaoFeng Wang, Deqing Zou, Hai Jin, Yuqing Zhang

Keywords Paper

Keywords Paper

Keywords Paper

Keywords Paper

Philipp Liznerski, Lukas Ruff, Robert A Vandermeulen and
Billy J Franks, Marius Kloft, Klaus R Muller

Keywords Paper

Tiangang Zhu, Yue Wang, Haoran Li and
Youzheng Wu, Xiaodong He, Bowen Zhou

Keywords Paper

Keywords Paper

Keywords Paper