R6P - Rolling shutter absolute pose problem

Albl, Cenek; Kúkelová, Zuzana; Pajdla, Tomáš

doi:10.1109/cvpr.2015.7298842

Cited by 44 publications

(75 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [15], a large-scale bundle adjustment with a generalized camera model is proposed and applied to 3D reconstructions from images collected with a rig of RS cameras. Several works [1,22,17] were introduced to solve the absolute pose estimation problem using RS cameras. All these efforts demonstrated the potential of applying 3D algorithms to RS cameras.…”

Section: Related Workmentioning

confidence: 99%

“…Due to the price advantage of the RS camera, many researchers began to propose 3D computer vision algorithms that aim to mitigate the RS effect over the recent years. Although several works have successfully demonstrated stereo [21], sparse and dense 3D reconstruction [15,23] and absolute pose estimation [1,22,17] using RS images, most of these works completely bypassed the initial relative pose estimation, e.g. by substituting it with GPS/INS readings.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rolling-Shutter-Aware Differential SfM and Image Rectification

Zhuang

Cheong

Lee

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this paper, we develop a modified differential Structure from Motion (SfM) algorithm that can estimate relative pose from two consecutive frames despite of Rolling Shutter (RS) artifacts. In particular, we show that under constant velocity assumption, the errors induced by the rolling shutter effect can be easily rectified by a linear scaling operation on each optical flow. We further propose a 9-point algorithm to recover the relative pose of a rolling shutter camera that undergoes constant acceleration motion. We demonstrate that the dense depth maps recovered from the relative pose of the RS camera can be used in a RS-aware warping for image rectification to recover high-quality Global Shutter (GS) images. Experiments on both synthetic and real RS images show that our RS-aware differential SfM algorithm produces more accurate results on relative pose estimation and 3D reconstruction from images distorted by RS effect compared to standard SfM algorithms that assume a GS camera model. We also demonstrate that our RS-aware warping for image rectification method outperforms stateof-the-art commercial software products, i.e. Adobe After Effects and Apple Imovie, at removing RS artifacts.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Rolling-Shutter-Aware Differential SfM and Image Rectification

Zhuang

Cheong

Lee

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…They first establish correspondences between pixels in a test image and 3D points in the scene. These 2D-3D matches are then used to estimate the camera pose by applying an npoint-pose (PnP) solver [2,[31][32][33][34] inside a RANSAC [18,22,36,54] loop. Traditionally, the first stage is based on matching descriptors extracted in the test image against descriptors associated with the 3D points.…”

Section: Introductionmentioning

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)

356

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

“…The proposed R6P is based on the constant linear and angular velocity model as in [14,16,1] but it uses the first order approximation to both the camera orientation and angular velocity, and, therefore, it requires an initialization of the camera orientation, e.g., from P3P [7]. Paper [18] has shown that R6P solver significantly outperforms perspective P3P solver in terms of camera pose precision and the number of inliers captured in the RANSAC loop.…”

Section: Introductionmentioning

confidence: 99%

Linear Solution to the Minimal Absolute Pose Rolling Shutter Problem

Kúkelová

Albl

Sugimoto

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

This paper presents new efficient solutions to the rolling shutter camera absolute pose problem. Unlike the state-of-the-art polynomial solvers, we approach the problem using simple and fast linear solvers in an iterative scheme. We present several solutions based on fixing different sets of variables and investigate the performance of them thoroughly. We design a new alternation strategy that estimates all parameters in each iteration linearly by fixing just the non-linear terms. Our best 6-point solver, based on the new alternation technique, shows an identical or even better performance than the state-of-the-art R6P solver and is two orders of magnitude faster. In addition, a linear noniterative solver is presented that requires a non-minimal number of 9 correspondences but provides even better results than the state-of-theart R6P. Moreover, all proposed linear solvers provide a single solution while the state-of-the-art R6P provides up to 20 solutions which have to be pruned by expensive verification.

show abstract

R6P - Rolling shutter absolute pose problem

Abstract: We present a minimal, non-iterative

Cited by 44 publications

References 23 publications

Rolling-Shutter-Aware Differential SfM and Image Rectification

Rolling-Shutter-Aware Differential SfM and Image Rectification

Understanding the Limitations of CNN-Based Absolute Camera Pose Regression

Linear Solution to the Minimal Absolute Pose Rolling Shutter Problem

Contact Info

Product

Resources

About