Large-Scale Location Recognition and the Geometric Burstiness Problem

Sattler, Torsten; Havlena, Michal; Schindler, Konrad; Pollefeys, Marc

doi:10.1109/cvpr.2016.175

Cited by 132 publications

(124 citation statements)

References 29 publications

Supporting

Mentioning

124

Contrasting

Order By: Relevance

“…Image retrieval is typically used for place recognition [3,5,17,58,71,72,77,80], i.e., for determining which part of a scene is visible in a given image. State-of-the-art approaches use compact image-level descriptors to enable efficient and scalable retrieval [3,52,71].…”

Section: Related Workmentioning

confidence: 99%

Understanding the Limitations of CNN-Based Absolute Camera Pose Regression

Sattler

Zhou

Pollefeys

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

332

270

View full text Add to dashboard Cite

Visual localization is the task of accurate camera pose estimation in a known scene. It is a key problem in computer vision and robotics, with applications including selfdriving cars, Structure-from-Motion, SLAM, and Mixed Reality. Traditionally, the localization problem has been tackled using 3D geometry. Recently, end-to-end approaches based on convolutional neural networks have become popular. These methods learn to directly regress the camera pose from an input image. However, they do not achieve the same level of pose accuracy as 3D structure-based methods. To understand this behavior, we develop a theoretical model for camera pose regression. We use our model to predict failure cases for pose regression techniques and verify our predictions through experiments. We furthermore use our model to show that pose regression is more closely related to pose approximation via image retrieval than to accurate pose estimation via 3D structure. A key result is that current approaches do not consistently outperform a handcrafted image retrieval baseline. This clearly shows that additional research is needed before pose regression algorithms are ready to compete with structure-based methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Understanding the Limitations of CNN-Based Absolute Camera Pose Regression

Sattler

Zhou

Pollefeys

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

332

270

View full text Add to dashboard Cite

show abstract

“…SIFT and DSP-SIFT. We employ a state-of-the-art visual localization pipeline [50,56] using SIFT [42]. This pipeline is based on a visual vocabulary tree embedded in a Hamming space [27] with visual burstiness weighting [28] and uses 2D-2D matching on the top-ranked retrievals to obtain 2D-3D correspondences for absolute pose estimation.…”

Section: Baselinesmentioning

confidence: 99%

Semantic Visual Localization

Schönberger

Pollefeys

Geiger

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

233

156

View full text Add to dashboard Cite

Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, e.g., in the context of life-long localization for augmented reality or autonomous robots. In this paper, we propose a novel approach based on a joint 3D geometric and semantic understanding of the world, enabling it to succeed under conditions where previous approaches failed. Our method leverages a novel generative model for descriptor learning, trained on semantic scene completion as an auxiliary task. The resulting 3D descriptors are robust to missing observations by encoding high-level 3D geometric and semantic information. Experiments on several challenging large-scale localization datasets demonstrate reliable localization under extreme viewpoint, illumination, and geometry changes.

show abstract

“…In practice, database images depicting an unrelated place may be more similar to the query estimated by the model than images come from the same place. This may be caused by repetitive structures and uninformative features existing in the database images (Sattler et al, 2016;Knopp et al, 2010). And as suggested by Schroff et al (2015), selecting those "very-hard" negatives can, in practice, lead to bad local minima early on in training.…”

Section: Semi-hard Negative Miningmentioning

confidence: 99%

Unified Vision‐Based Methodology for Simultaneous Concrete Defect Detection and Geolocalization

Yuan

Zhang

et al. 2018

Computer aided Civil Eng

113

View full text Add to dashboard Cite

Vision‐based autonomous inspection of concrete surface defects is crucial for efficient maintenance and rehabilitation of infrastructures and has become a research hot spot. However, most existing vision‐based inspection methods mainly focus on detecting one kind of defect in nearly uniform testing background where defects are relatively large and easily recognizable. But in the real‐world scenarios, multiple types of defects often occur simultaneously. And most of them occupy only small fractions of inspection images and are swamped in cluttered background, which easily leads to missed and false detections. In addition, the majority of the previous researches only focus on detecting defects but few of them pay attention to the geolocalization problem, which is indispensable for timely performing repair, protection, or reinforcement works. And most of them rely heavily on GPS for tracking the locations of the defects. However, this method is sometimes unreliable within infrastructures where the GPS signals are easily blocked, which causes a dramatic increase in searching costs. To address these limitations, we present a unified and purely vision‐based method denoted as defects detection and localization network, which can detect and classify various typical types of defects under challenging conditions while simultaneously geolocating the defects without requiring external localization sensors. We design a supervised deep convolutional neural network and propose novel training methods to optimize its performance on specific tasks. Extensive experiments show that the proposed method is effective with a detection accuracy of 80.7% and a localization accuracy of 86% at 0.41 s per image (at a scale of 1,200 pixels in the field test experiment), which is ideal for integration within intelligent autonomous inspection systems to provide support for practical applications.

show abstract

Large-Scale Location Recognition and the Geometric Burstiness Problem

Cited by 132 publications

References 29 publications

Understanding the Limitations of CNN-Based Absolute Camera Pose Regression

Understanding the Limitations of CNN-Based Absolute Camera Pose Regression

Semantic Visual Localization

Unified Vision‐Based Methodology for Simultaneous Concrete Defect Detection and Geolocalization

Contact Info

Product

Resources

About