CNN-Augmented Visual-Inertial SLAM with Planar Constraints
- URL: http://arxiv.org/abs/2205.02940v1
- Date: Thu, 5 May 2022 21:49:57 GMT
- Title: CNN-Augmented Visual-Inertial SLAM with Planar Constraints
- Authors: Pan Ji, Yuan Tian, Qingan Yan, Yuxin Ma, and Yi Xu
- Abstract summary: We present a robust visual-inertial SLAM system that combines the benefits of Convolutional Neural Networks (CNNs) and planar constraints.
We use a CNN to predict the depth map and the corresponding uncertainty map for each image.
We also present a fast plane detection method that detects horizontal planes via one-point RANSAC and vertical planes via two-point RANSAC.
- Score: 26.024485121674328
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We present a robust visual-inertial SLAM system that combines the benefits of
Convolutional Neural Networks (CNNs) and planar constraints. Our system
leverages a CNN to predict the depth map and the corresponding uncertainty map
for each image. The CNN depth effectively bootstraps the back-end optimization
of SLAM and meanwhile the CNN uncertainty adaptively weighs the contribution of
each feature point to the back-end optimization. Given the gravity direction
from the inertial sensor, we further present a fast plane detection method that
detects horizontal planes via one-point RANSAC and vertical planes via
two-point RANSAC. Those stably detected planes are in turn used to regularize
the back-end optimization of SLAM. We evaluate our system on a public dataset,
\ie, EuRoC, and demonstrate improved results over a state-of-the-art SLAM
system, \ie, ORB-SLAM3.
Related papers
- KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filter [49.85369344101118]
We introduce KFD-NeRF, a novel dynamic neural radiance field integrated with an efficient and high-quality motion reconstruction framework based on Kalman filtering.
Our key idea is to model the dynamic radiance field as a dynamic system whose temporally varying states are estimated based on two sources of knowledge: observations and predictions.
Our KFD-NeRF demonstrates similar or even superior performance within comparable computational time and state-of-the-art view synthesis performance with thorough training.
arXiv Detail & Related papers (2024-07-18T05:48:24Z) - SLAIM: Robust Dense Neural SLAM for Online Tracking and Mapping [15.63276368052395]
We propose a novel coarse-to-fine tracking model tailored for Neural Radiance Field SLAM (NeRF-SLAM)
Existing NeRF-SLAM systems consistently exhibit inferior tracking performance compared to traditional SLAM algorithms.
We implement both local and global bundle-adjustment to produce a robust (coarse-to-fine) and accurate (KL regularizer) SLAM solution.
arXiv Detail & Related papers (2024-04-17T14:23:28Z) - Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy [75.15685966213832]
We analyze the rich directional structure of optimization trajectories represented by their pointwise parameters.
We show that training only scalar batchnorm parameters some while into training matches the performance of training the entire network.
arXiv Detail & Related papers (2024-03-12T07:32:47Z) - GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system.
Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering.
Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
arXiv Detail & Related papers (2023-11-20T12:08:23Z) - UncLe-SLAM: Uncertainty Learning for Dense Neural SLAM [60.575435353047304]
We present an uncertainty learning framework for dense neural simultaneous localization and mapping (SLAM)
We propose an online framework for sensor uncertainty estimation that can be trained in a self-supervised manner from only 2D input data.
arXiv Detail & Related papers (2023-06-19T16:26:25Z) - VP-SLAM: A Monocular Real-time Visual SLAM with Points, Lines and
Vanishing Points [31.55798962786664]
We present a real-time monocular Visual SLAM system that incorporates real-time methods for line and VP extraction.
We also present two strategies that exploit vanishing points to estimate the robot's translation and improve its rotation.
The proposed system achieves state-of-the-art results and runs in real time, and its performance remains close to the original ORB-SLAM2 system.
arXiv Detail & Related papers (2022-10-23T15:54:26Z) - Structure PLP-SLAM: Efficient Sparse Mapping and Localization using
Point, Line and Plane for Monocular, RGB-D and Stereo Cameras [13.693353009049773]
This paper demonstrates a visual SLAM system that utilizes point and line cloud for robust camera localization, simultaneously, with an embedded piece-wise planar reconstruction (PPR) module.
We address the challenge of reconstructing geometric primitives with scale ambiguity by proposing several run-time optimizations on the reconstructed lines and planes.
The results show that our proposed SLAM tightly incorporates the semantic features to boost both tracking as well as backend optimization.
arXiv Detail & Related papers (2022-07-13T09:05:35Z) - 3DVNet: Multi-View Depth Prediction and Volumetric Refinement [68.68537312256144]
3DVNet is a novel multi-view stereo (MVS) depth-prediction method.
Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions.
We show that our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics.
arXiv Detail & Related papers (2021-12-01T00:52:42Z) - Online Adaptation of Monocular Depth Prediction with Visual SLAM [8.478040209440868]
The ability of accurate depth prediction by a CNN is a major challenge for its wide use in practical visual SLAM applications.
We propose a novel online adaptation framework consisting of two complementary processes to fine-tune the depth prediction.
Experimental results on both benchmark datasets and a real robot in our own experimental environments show that our proposed method improves the SLAM reconstruction accuracy.
arXiv Detail & Related papers (2021-11-07T14:20:35Z) - Greedy-Based Feature Selection for Efficient LiDAR SLAM [12.257338124961622]
This paper demonstrates that actively selecting a subset of features significantly improves both the accuracy and efficiency of an L-SLAM system.
We show that our approach exhibits low localization error and speedup compared to the state-of-the-art L-SLAM systems.
arXiv Detail & Related papers (2021-03-24T11:03:16Z) - Pushing the Envelope of Rotation Averaging for Visual SLAM [69.7375052440794]
We propose a novel optimization backbone for visual SLAM systems.
We leverage averaging to improve the accuracy, efficiency and robustness of conventional monocular SLAM systems.
Our approach can exhibit up to 10x faster with comparable accuracy against the state-art on public benchmarks.
arXiv Detail & Related papers (2020-11-02T18:02:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.