Worldwide Pose Estimation Using 3D Point Clouds

By Yunpeng Li, Noah Snavely, Dan Huttenlocher, Pascal Fua. 2012

439 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps (2018, methodology): “Pose estimation approaches [9,18,19,20,21,22,23] match query images against 3D models of an area, and employ 2D-3D feature correspondences to identify 6-DOF query poses.”
PlaNet - Photo Geolocation with Convolutional Neural Networks (2016, methodology): “…subsets of the problem, like landmark build-1 ings [1, 37, 54], cities where street view imagery is available [7, 26, 52], or places where coverage of internet photos is dense enough to allow building a structure-from-motion reconstruction that a query photo can be matched against [31, 41].”
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition (2015, background): “8]. The resulting representation is then usually compressed and efﬁ- ciently indexed [27,69]. The image database can be further augmented by 3D structure that enables recovery of accurate camera pose [38,58,59]. In the last few years convolutional neural networks (CNNs) [36,37] have emerged as power”
Learning Less is More - 6D Camera Localization via 3D Surface Regression (2017, background): “Research focused on making descriptor matching efficient [15], robust [25, 19] and scale to large outdoor environments [14, 18, 20].”
Google Landmarks Dataset v2 – A Large-Scale Benchmark for Instance-Level Recognition and Retrieval (2020, neutral): “[35] Instance-level recognition datasets.”
MegaDepth: Learning Single-View Depth Prediction from Internet Photos (2018, methodology): “We first download Internet photos from Flickr for a set of well-photographed landmarks from the Landmarks10K dataset [21].”
Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views (2015, neutral): “, [10, 34, 45], typically based on SIFT matching [37] with geometric constraints.”
Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization (2015, methodology): “We compare using a kd-tree [13] (as in [25, 49]), a normal inverted index (as in [41, 42]), and an inverted multi-index.”
Graph-Based Discriminative Learning for Location Recognition (2013, methodology): “However, there is no single definition for what it means to be a location, and, accordingly, a wide variety of representations for places have been used in research: Are places, for instance, a set of distinct landmarks, each represented by a set of images? [33, 16] Are places latitude and longitude”
Image-Based Localization Using LSTMs for Structured Feature Correlation (2016, methodology): “Most state-of-the-art approaches [30, 43, 48, 60] rely on local features such as SIFT [34] to solve the problem of image-based localization.”
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features (2019, methodology): “Sparse features offer a memory ef-ﬁcient representation and thus enable approaches such as Structure-from-Motion (SfM) [21,53] or visual localization [26, 47, 58] to scale.”
Modelling uncertainty in deep learning for camera relocalization (2015, background): “Visual SLAM [1], [4], [5], [9], and relocalization research [10], [11], has largely focused on registering viewpoints using point-based landmark features, such as SIFT [2] or ORB [3].”
Privacy Preserving Image-Based Localization (2019, methodology): “Recent progress in imagebased localization has led to methods that are now quite robust to changes in scene appearance and illumination [4,62], scale to large scenes [43,57,59,84], and are suitable for realtime computation and mobile devices [8, 33, 35, 43–45, 58, 77] with compressed map representat”
Learning and Calibrating Per-Location Classifiers for Visual Place Recognition (2013, background): “Examples include: (i) building an explicit 3D reconstruction of the scene [10, 15, 16]; (ii) constructing an image graph [24, 30], where images are nodes and edges connect close-by images on the map [29], or (iii) using the geotagged data as a form of supervision to select local features that…”
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions (2018, methodology): “52M (69) 15,179 1000 San Francisco [16, 34, 57] Urban Free Viewpoint 30M / 149M (1) 610,773 442 X(SfM) Vienna [29] Landmarks Free Viewpoint 1.”
Learned Contextual Feature Reweighting for Image Geo-Localization (2017, methodology): “Image geo-localization has been cast as an image retrieval task [2, 10, 19, 28, 66], a 2D to 3D registration task [17, 21, 32, 47, 46], and a per-location classification task [16, 62].”
Visual landmark recognition from Internet photo collections: A large-scale evaluation (2014, background): “Other approaches are based on 3D point clouds created by applying structure-frommotion on Internet photo collections or manually collected photos [36, 37, 21, 23].”