MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints

Wang, Yuping; Manocha, Dinesh

doi:10.48550/arxiv.2109.06768

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the main assumptions of the original unsupervised training formulation is that the world is static. Hence, many works investigate informing the learning process about moving objects through optical flow [ 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 ]. The optical flow, which represents dense maps of the pixel coordinates displacement, can be separated into two components.…”

Section: Related Workmentioning

confidence: 99%

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

Cimarelli

Bavle

Sánchez-López

et al. 2022

Sensors

View full text Add to dashboard Cite

Unsupervised learning for monocular camera motion and 3D scene understanding has gained popularity over traditional methods, which rely on epipolar geometry or non-linear optimization. Notably, deep learning can overcome many issues of monocular vision, such as perceptual aliasing, low-textured areas, scale drift, and degenerate motions. In addition, concerning supervised learning, we can fully leverage video stream data without the need for depth or motion labels. However, in this work, we note that rotational motion can limit the accuracy of the unsupervised pose networks more than the translational component. Therefore, we present RAUM-VO, an approach based on a model-free epipolar constraint for frame-to-frame motion estimation (F2F) to adjust the rotation during training and online inference. To this end, we match 2D keypoints between consecutive frames using pre-trained deep networks, Superpoint and Superglue, while training a network for depth and pose estimation using an unsupervised training protocol. Then, we adjust the predicted rotation with the motion estimated by F2F using the 2D matches and initializing the solver with the pose network prediction. Ultimately, RAUM-VO shows a considerable accuracy improvement compared to other unsupervised pose networks on the KITTI dataset, while reducing the complexity of other hybrid or traditional approaches and achieving comparable state-of-the-art results.

show abstract

Section: Related Workmentioning

confidence: 99%

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

Cimarelli

Bavle

Sánchez-López

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…One of the main assumptions of the original unsupervised training formulation is that the world is static. Hence, many works investigate informing the learning process about moving objects through optical flow [41,42,43,44,45,46,47,48,49,50,51,52]. The optical flow, which represents dense maps of the pixel coordinates displacement, can be separated into two components.…”

Section: Related Workmentioning

confidence: 99%

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

Cimarelli¹,

Bavle²,

Sánchez-López³

et al. 2022

Preprint

View full text Add to dashboard Cite

Unsupervised learning for monocular camera motion and 3D scene understanding has gained popularity over traditional methods, relying on epipolar geometry or non-linear optimization. Notably, deep learning can overcome many issues of monocular vision, such as perceptual aliasing, lowtextured areas, scale-drift, and degenerate motions. Also, concerning supervised learning, we can fully leverage video streams data without the need for depth or motion labels. However, in this work, we note that rotational motion can limit the accuracy of the unsupervised pose networks more than the translational component. Therefore, we present RAUM-VO, an approach based on a model-free epipolar constraint for frame-to-frame motion estimation (F2F) to adjust the rotation during training and online inference. To this end, we match 2D keypoints between consecutive frames using pre-trained deep networks, Superpoint and Superglue, while training a network for depth and pose estimation using an unsupervised training protocol. Then, we adjust the predicted rotation with the motion estimated by F2F using the 2D matches and initializing the solver with the pose network prediction. Ultimately, RAUM-VO shows a considerable accuracy improvement compared to other unsupervised pose networks on the KITTI dataset while reducing the complexity of other hybrid or traditional approaches and achieving comparable state-of-the-art results.

show abstract

MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints

Cited by 2 publications

References 20 publications

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry

Contact Info

Product

Resources

About