Adversarial Networks for Camera Pose Regression and Refinement

Bui, Mai; Baur, Christoph; Navab, Nassir; Ilić, Slobodan; Albarqouni, Shadi

doi:10.1109/iccvw.2019.00470

Cited by 20 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This not only regresses the pose but could also refine the pose. When extracting features, AdPR [104] applies the ResNet-18 Network, as it can achieve the best performance when compared with VGG16 and AlexNet.…”

Section: ) Learnable Pose Loss Parametersmentioning

confidence: 99%

A Critical Analysis of Image-based Camera Pose Estimation Techniques

Xu¹,

Wang²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR). After decades of progress, camera localization, also called camera pose estimation could compute the 6DoF pose of objects for a camera in a given image, with respect to different images in a sequence or formats. Structure-based localization methods have achieved great success when integrated with image matching or with a coordinate regression stage. Absolute and relative pose regression methods using transfer learning can support end-to-end localisation to directly regress a camera pose but achieve a less accurate performance. Despite the rapid development of multiple branches in this area, a comprehensive, in-depth and comparative analysis is lacking to summarise, classify and compare, structure-based and regression-based camera localization methods. Existing surveys either focus on larger SLAM (Simultaneous Localization and Mapping) systems or on only part of the camera localization method, lack detailed comparisons and descriptions of the methods or datasets used, neural network designs such as loss designs, and input formats, etc. In this survey, we first introduce specific application areas and the evaluation metrics for camera localization pose according to different sub-

show abstract

Section: ) Learnable Pose Loss Parametersmentioning

confidence: 99%

A Critical Analysis of Image-based Camera Pose Estimation Techniques

Xu¹,

Wang²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Such methods perform well under appearance and limited viewpoint changes [84]. Direct pose regression methods, which aim to directly regress a pose from the query image, are often based on pose regression networks [1, 49-51, 68, 107], although decision forest [47], GAN [20] and LSTM [29,103] variants also exist. On the whole, they have not yet matched the precision of state-of-the-art structure-based and RGB-D methods indoors.…”

Section: Related Workmentioning

confidence: 99%

Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes

Wald¹,

Sattler²,

Golodetz³

et al. 2020

Preprint

View full text Add to dashboard Cite

Long-term camera re-localization is an important task with numerous computer vision and robotics applications. Whilst various outdoor benchmarks exist that target lighting, weather and seasonal changes, far less attention has been paid to appearance changes that occur indoors. This has led to a mismatch between popular indoor benchmarks, which focus on static scenes, and indoor environments that are of interest for many real-world applications. In this paper, we adapt 3RScan -a recently introduced indoor RGB-D dataset designed for object instance re-localization -to create RIO10, a new long-term camera re-localization benchmark focused on indoor scenes. We propose new metrics for evaluating camera re-localization and explore how state-of-the-art camera re-localizers perform according to these metrics. We also examine in detail how different types of scene change affect the performance of different methods, based on novel ways of detecting such changes in a given RGB-D frame. Our results clearly show that long-term indoor re-localization is an unsolved problem. Our benchmark and tools are publicly available at waldjohannau.github.io/RIO10.

show abstract

“…age's pose, using e.g. decision forests [32], pose regression networks [36,34,35,47,72,1], GANs [10] or LSTMs [15,70]. Various recent approaches [9,57,67,40] have made use of the relative poses between images to improve performance.…”

Section: Back-project Pointsmentioning

confidence: 99%

Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation

Cavallari

Bertinetto

Mukhoti

et al. 2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can be used online, the former often fail away from the training trajectory, and the latter can struggle in textureless regions. By contrast, scene coordinate regression (SCoRe) methods generalise to novel poses and can leverage dense correspondences to improve robustness, and recent work has shown how to adapt SCoRe forests between scenes, allowing their state-of-the-art performance to be leveraged online. However, because they use features hand-crafted for indoor use, they do not generalise well to harder outdoor scenes. Whilst replacing the forest with a neural network and learning suitable features for outdoor use is possible, the techniques used to adapt forests between scenes are unfortunately harder to transfer to a network context. In this paper, we address this by proposing a novel way of leveraging a network trained on one scene to predict points in another scene. Our approach replaces the appearance clustering performed by the branching structure of a regression forest with a two-step process that first uses the network to predict points in the original scene, and then uses these predicted points to look up clusters of points from the new scene. We show experimentally that our online approach achieves state-of-the-art performance on both the 7-Scenes and Cambridge Landmarks datasets, whilst running in under 300ms, making it highly effective in live scenarios.

show abstract

Adversarial Networks for Camera Pose Regression and Refinement

Cited by 20 publications

References 41 publications

A Critical Analysis of Image-based Camera Pose Estimation Techniques

A Critical Analysis of Image-based Camera Pose Estimation Techniques

Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes

Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation

Contact Info

Product

Resources

About