VOLDOR: Visual Odometry From Log-Logistic Dense Optical Flow Residuals

Min, Zhixiang; Yang, Yiding; Dunn, Enrique

doi:10.1109/cvpr42600.2020.00495

Cited by 39 publications

(17 citation statements)

References 100 publications

(109 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Deep learning has gained impressive progress in visual odometry [8], [9]. However, the 3D LiDAR odometry with deep learning is still a challenging problem.…”

Section: Deep Lidar Odometrymentioning

confidence: 99%

“…It is found that learning-based methods can deal with sparse features and dynamic environments [1], [2], which are usually difficult for conventional methods. To our knowledge, most learning-based methods are on the 2D visual odometry [3], [4], [5], [6], [7], [8], [9] or utilize 2D convolution on the projected information of LiDAR [10], [11], [12], [13], [14]. 3D learning methods from the raw point cloud have been developed rapidly and have recently made remarkable progress on many problem [15], [16], [17], [18], [19], while the deep LiDAR odometry in 3D point clouds is underexplored.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient 3D Deep LiDAR Odometry

Wang¹,

Wu²,

Jiang³

et al. 2021

Preprint

View full text Add to dashboard Cite

An efficient 3D point cloud learning architecture, named PWCLO-Net, for LiDAR odometry is first proposed in this paper. In this architecture, the projection-aware representation of the 3D point cloud is proposed to organize the raw 3D point cloud into an ordered data form to achieve efficiency. The Pyramid, Warping, and Cost volume (PWC) structure for the LiDAR odometry task is built to estimate and refine the pose in a coarse-to-fine approach hierarchically and efficiently. A projection-aware attentive cost volume is built to directly associate two discrete point clouds and obtain embedding motion patterns. Then, a trainable embedding mask is proposed to weigh the local motion patterns to regress the overall pose and filter outlier points. The trainable pose warp-refinement module is iteratively used with embedding mask optimized hierarchically to make the pose estimation more robust for outliers. The entire architecture is holistically optimized end-to-end to achieve adaptive learning of cost volume and mask, and all operations involving point cloud sampling and grouping are accelerated by projection-aware 3D feature learning methods. The superior performance and effectiveness of our LiDAR odometry architecture are demonstrated on KITTI odometry dataset. Our method outperforms all recent learning-based methods and even the geometry-based approach, LOAM with mapping optimization, on most sequences of KITTI odometry dataset.

show abstract

“…Deep learning has gained impressive progress in visual odometry [8], [9]. However, the 3D LiDAR odometry with deep learning is still a challenging problem.…”

Section: Deep Lidar Odometrymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient 3D Deep LiDAR Odometry

Wang¹,

Wu²,

Jiang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…As it can be seen, the best performing method used Colmap [33], a Structure-from- 1.09 0.0033 ORB-SLAM [2] 1.15 0.0027 S-PTAM [31] 1.19 0.0025 RTAB-Map [32] 1.26 0.0026 Motion (SfM) library, along with deep features [34], [35] for matching. The second best performing method was based on Voldor [36], a dense VSLAM methods that computes residual flow for pose estimation, along with Colmap to scale the estimated translation. OV 2 SLAM ranks 3rd on both the monocular and stereo tracks of this challenge and is actually the 1st if we only consider online methods, i.e.…”

Section: Tartanair Datasetmentioning

confidence: 99%

OV$^{2}$SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications

Ferrera¹,

Eudes²,

Moras³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many applications of Visual SLAM, such as augmented reality, virtual reality, robotics or autonomous driving, require versatile, robust and precise solutions, most often with real-time capability. In this work, we describe OV 2 SLAM, a fully online algorithm, handling both monocular and stereo camera setups, various map scales and frame-rates ranging from a few Hertz up to several hundreds. It combines numerous recent contributions in visual localization within an efficient multi-threaded architecture. Extensive comparisons with competing algorithms shows the state-of-the-art accuracy and real-time performance of the resulting algorithm. For the benefit of the community, we release the source code: https://github.com/ov2slam/ov2slam.

show abstract

“…O PTICAL flow represents the 2D motion and correspondence relationship between two images at the pixel level, which is a fundamental problem in the field of computer vision. Optical flow has lots of applications in autonomous driving, such as visual odometry [1], target tracking [2], moving object detection, and mapping [3], [4]. In addition, the optical flow can be used to analyze the motion attributes of pedestrians and vehicles, so as to realize the dynamic understanding of scenes and decision-making.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Learning of Depth, Optical Flow and Pose With Occlusion From 3D Geometry

Wang

Zhang

Wang

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Optical flow estimation is a fundamental problem of computer vision and has many applications in the fields of robot learning and autonomous driving. This paper reveals novel geometric laws of optical flow based on the insight and detailed definition of non-occlusion. Then, two novel loss functions are proposed for the unsupervised learning of optical flow based on the geometric laws of non-occlusion. Specifically, after the occlusion part of the images are masked, the flowing process of pixels is carefully considered and geometric constraints are conducted based on the geometric laws of optical flow. First, neighboring pixels in the first frame will not intersect during the pixel displacement to the second frame. Secondly, when the cluster containing adjacent four pixels in the first frame moves to the second frame, no other pixels will flow into the quadrilateral formed by them. According to the two geometrical constraints, the optical flow non-intersection loss and the optical flow non-blocking loss in the non-occlusion regions are proposed. Two loss functions punish the irregular and inexact optical flows in the non-occlusion regions. The experiments on datasets demonstrated that the proposed unsupervised losses of optical flow based on the geometric laws in non-occlusion regions make the estimated optical flow more refined in detail, and improve the performance of unsupervised learning of optical flow. In addition, the experiments training on synthetic data and evaluating on real data show that the generalization ability of optical flow network is improved by our proposed unsupervised approach.

show abstract

VOLDOR: Visual Odometry From Log-Logistic Dense Optical Flow Residuals

Cited by 39 publications

References 100 publications

Efficient 3D Deep LiDAR Odometry

Efficient 3D Deep LiDAR Odometry

OV$^{2}$SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications

Unsupervised Learning of Depth, Optical Flow and Pose With Occlusion From 3D Geometry

Contact Info

Product

Resources

About