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

  title={VOLDOR: Visual Odometry From Log-Logistic Dense Optical Flow Residuals},
  author={Zhixiang Min and Yiding Yang and Enrique Dunn},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
We propose a dense indirect visual odometry method taking as input externally estimated optical flow fields instead of hand-crafted feature correspondences. We define our problem as a probabilistic model and develop a generalized-EM formulation for the joint inference of camera motion, pixel depth, and motion-track confidence. Contrary to traditional methods assuming Gaussian-distributed observation errors, we supervise our inference framework under an (empirically validated) adaptive log… Expand
VOLDOR-SLAM: For the Times When Feature-Based or Direct Methods Are Not Good Enough
The recent probabilistic visual odometry model VOLDOR is extended, by incorporating the use of geometric priors to robustly bootstrap estimation from monocular capture, while seamlessly supporting stereo and/or RGB-D input imagery. Expand
Depth distillation: unsupervised metric depth estimation for UAVs by finding consensus between kinematics, optical flow and deep learning
Estimating precise metric depth is an essential task for UAV navigation, which is very difficult to learn unsupervised without access to odometry. At the same time, depth recovery from kinematics andExpand
DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras
We introduce DROID-SLAM, a new deep learning based SLAM system. DROIDSLAM consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense Bundle Adjustment layer.Expand
NccFlow: Unsupervised Learning of Optical Flow With Non-occlusion from Geometry
  • Guangming Wang, Shuaiqi Ren, Hesheng Wang
  • Computer Science
  • ArXiv
  • 2021
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 unsuper supervised learning of Optical flow. Expand
OVSLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications
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. InExpand
OV$^{2}$SLAM: A Fully Online and Versatile Visual SLAM for Real-Time Applications
OV$^{2}$SLAM is described, 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, and combines numerous recent contributions in visual localization within an efficient multi-threaded architecture. Expand
A Heteroscedastic Likelihood Model for Two-Frame Optical Flow
A new class of likelihood functions that characterises the uncertainty of the error distribution of two-frame optical flow that enables a heteroscedastic dependence on texture is proposed and demonstrated in a visual odometry ego-motion study. Expand
Hierarchical Attention Learning of Scene Flow in 3D Point Clouds
A novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer, which outperforms the ICP-based method and shows good practical application ability. Expand
PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization
The PWCLO-Net method outperforms all recent learning-based methods and outperforms the geometry-based approach, LOAM with mapping optimization, on most sequences of the KITTI odometry dataset. Expand


Multimodal scale estimation for monocular visual odometry
This work addresses the problem of monocular scale estimation by proposing a multimodal mechanism of prediction, classification, and correction and employs classifiers to detect scale outliers based on various features (e.g. moments on residuals). Expand
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
An adaptive geometric consistency loss is proposed to increase robustness towards outliers and non-Lambertian regions, which resolves occlusions and texture ambiguities effectively and achieves state-of-the-art results in all of the three tasks, performing better than previously unsupervised methods and comparably with supervised ones. Expand
Predictive monocular odometry (PMO): What is possible without RANSAC and multiframe bundle adjustment?
A robust monocular visual odometry framework for automotive applications that achieves a higher rank than current published state-of-the-art monocular methods in the KITTI odometry benchmark and challenges the common belief that robust systems can only be built using iterative robustification tools like RANSAC. Expand
Direct Sparse Odometry
The experiments show that the presented approach significantly outperforms state-of-the-art direct and indirect methods in a variety of real-world settings, both in terms of tracking accuracy and robustness. Expand
Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry
This work presents a VO framework by incorporating two additional components called Memory and Refining, which achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic VO algorithms tend to fail. Expand
Dense visual SLAM for RGB-D cameras
This paper proposes a dense visual SLAM method for RGB-D cameras that minimizes both the photometric and the depth error over all pixels, and proposes an entropy-based similarity measure for keyframe selection and loop closure detection. Expand
SVO: Fast semi-direct monocular visual odometry
A semi-direct monocular visual odometry algorithm that is precise, robust, and faster than current state-of-the-art methods and applied to micro-aerial-vehicle state-estimation in GPS-denied environments is proposed. Expand
UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos
This paper proposes UnOS, an unified system for unsupervised optical flow and stereo depth estimation using convolutional neural network (CNN) by taking advantages of their inherent geometrical consistency based on the rigid-scene assumption, and derives a rigid-aware direct visual odometry (RDVO) module. Expand
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes
Experimental results on various benchmarking datasets show that the Deep Epipolar Flow method achieves competitive performance compared with supervised methods and outperforms state-of-the-art unsupervised deep-learning methods. Expand
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
The use of stereo sequences for learning depth and visual odometry enables the use of both spatial and temporal photometric warp error, and constrains the scene depth and camera motion to be in a common, real-world scale. Expand