Monocular visual odometry is the process of estimating the motion of a camera using a single camera and visual features.
For the task of simultaneous monocular depth and visual odometry estimation, we propose learning self-supervised transformer-based models in two steps. Our first step consists in a generic pretraining to learn 3D geometry, using cross-view completion objective (CroCo), followed by self-supervised finetuning on non-annotated videos. We show that our self-supervised models can reach state-of-the-art performance 'without bells and whistles' using standard components such as visual transformers, dense prediction transformers and adapters. We demonstrate the effectiveness of our proposed method by running evaluations on six benchmark datasets, both static and dynamic, indoor and outdoor, with synthetic and real images. For all datasets, our method outperforms state-of-the-art methods, in particular for depth prediction task.
Monocular visual odometry is a key technology in a wide variety of autonomous systems. Relative to traditional feature-based methods, that suffer from failures due to poor lighting, insufficient texture, large motions, etc., recent learning-based SLAM methods exploit iterative dense bundle adjustment to address such failure cases and achieve robust accurate localization in a wide variety of real environments, without depending on domain-specific training data. However, despite its potential, learning-based SLAM still struggles with scenarios involving large motion and object dynamics. In this paper, we diagnose key weaknesses in a popular learning-based SLAM model (DROID-SLAM) by analyzing major failure cases on outdoor benchmarks and exposing various shortcomings of its optimization process. We then propose the use of self-supervised priors leveraging a frozen large-scale pre-trained monocular depth estimation to initialize the dense bundle adjustment process, leading to robust visual odometry without the need to fine-tune the SLAM backbone. Despite its simplicity, our proposed method demonstrates significant improvements on KITTI odometry, as well as the challenging DDAD benchmark. Code and pre-trained models will be released upon publication.
Visual-inertial odometry (VIO) has demonstrated remarkable success due to its low-cost and complementary sensors. However, existing VIO methods lack the generalization ability to adjust to different environments and sensor attributes. In this paper, we propose Adaptive VIO, a new monocular visual-inertial odometry that combines online continual learning with traditional nonlinear optimization. Adaptive VIO comprises two networks to predict visual correspondence and IMU bias. Unlike end-to-end approaches that use networks to fuse the features from two modalities (camera and IMU) and predict poses directly, we combine neural networks with visual-inertial bundle adjustment in our VIO system. The optimized estimates will be fed back to the visual and IMU bias networks, refining the networks in a self-supervised manner. Such a learning-optimization-combined framework and feedback mechanism enable the system to perform online continual learning. Experiments demonstrate that our Adaptive VIO manifests adaptive capability on EuRoC and TUM-VI datasets. The overall performance exceeds the currently known learning-based VIO methods and is comparable to the state-of-the-art optimization-based methods.
Drones are increasingly used in fields like industry, medicine, research, disaster relief, defense, and security. Technical challenges, such as navigation in GPS-denied environments, hinder further adoption. Research in visual odometry is advancing, potentially solving GPS-free navigation issues. Traditional visual odometry methods use geometry-based pipelines which, while popular, often suffer from error accumulation and high computational demands. Recent studies utilizing deep neural networks (DNNs) have shown improved performance, addressing these drawbacks. Deep visual odometry typically employs convolutional neural networks (CNNs) and sequence modeling networks like recurrent neural networks (RNNs) to interpret scenes and deduce visual odometry from video sequences. This paper presents a novel real-time monocular visual odometry model for drones, using a deep neural architecture with a self-attention module. It estimates the ego-motion of a camera on a drone, using consecutive video frames. An inference utility processes the live video feed, employing deep learning to estimate the drone's trajectory. The architecture combines a CNN for image feature extraction and a long short-term memory (LSTM) network with a multi-head attention module for video sequence modeling. Tested on two visual odometry datasets, this model converged 48% faster than a previous RNN model and showed a 22% reduction in mean translational drift and a 12% improvement in mean translational absolute trajectory error, demonstrating enhanced robustness to noise.
This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently Gaussian Splatting-based SLAM has yielded promising results, but rely on RGB-D input and is weak in tracking. To address these limitations, we uniquely integrates advanced sparse visual odometry with a dense Gaussian Splatting scene representation for the first time, thereby eliminating the dependency on depth maps typical of Gaussian Splatting-based SLAM systems and enhancing tracking robustness. Here, the sparse visual odometry tracks camera poses in RGB stream, while Gaussian Splatting handles map reconstruction. These components are interconnected through a Multi-View Stereo (MVS) depth estimation network. And we propose a depth smooth loss to reduce the negative effect of estimated depth maps. Furthermore, the consistency in scale between the sparse visual odometry and the dense Gaussian map is preserved by Sparse-Dense Adjustment Ring (SDAR). We have evaluated our system across various synthetic and real-world datasets. The accuracy of our pose estimation surpasses existing methods and achieves state-of-the-art performance. Additionally, it outperforms previous monocular methods in terms of novel view synthesis fidelity, matching the results of neural SLAM systems that utilize RGB-D input.
Deep learning techniques have significantly advanced in providing accurate visual odometry solutions by leveraging large datasets. However, generating uncertainty estimates for these methods remains a challenge. Traditional sensor fusion approaches in a Bayesian framework are well-established, but deep learning techniques with millions of parameters lack efficient methods for uncertainty estimation. This paper addresses the issue of uncertainty estimation for pre-trained deep-learning models in monocular visual odometry. We propose formulating a factor graph on an implicit layer of the deep learning network to recover relative covariance estimates, which allows us to determine the covariance of the Visual Odometry (VO) solution. We showcase the consistency of the deep learning engine's covariance approximation with an empirical analysis of the covariance model on the EUROC datasets to demonstrate the correctness of our formulation.
We present COMO, a real-time monocular mapping and odometry system that encodes dense geometry via a compact set of 3D anchor points. Decoding anchor point projections into dense geometry via per-keyframe depth covariance functions guarantees that depth maps are joined together at visible anchor points. The representation enables joint optimization of camera poses and dense geometry, intrinsic 3D consistency, and efficient second-order inference. To maintain a compact yet expressive map, we introduce a frontend that leverages the covariance function for tracking and initializing potentially visually indistinct 3D points across frames. Altogether, we introduce a real-time system capable of estimating accurate poses and consistent geometry.
We present the POLAR Traverse Dataset: a dataset of high-fidelity stereo pair images of lunar-like terrain under polar lighting conditions designed to simulate a straight-line traverse. Images from individual traverses with different camera heights and pitches were recorded at 1 m intervals by moving a suspended stereo bar across a test bed filled with regolith simulant and shaped to mimic lunar south polar terrain. Ground truth geometry and camera position information was also recorded. This dataset is intended for developing and testing software algorithms that rely on stereo or monocular camera images, such as visual odometry, for use in the lunar polar environment, as well as to provide insight into the expected lighting conditions in lunar polar regions.
Deep learning algorithms have driven expressive progress in many complex tasks. The loss function is a core component of deep learning techniques, guiding the learning process of neural networks. This paper contributes by introducing a consistency loss for visual odometry with deep learning-based approaches. The motion consistency loss explores repeated motions that appear in consecutive overlapped video clips. Experimental results show that our approach increased the performance of a model on the KITTI odometry benchmark.
We introduce a novel monocular visual odometry (VO) system, NeRF-VO, that integrates learning-based sparse visual odometry for low-latency camera tracking and a neural radiance scene representation for sophisticated dense reconstruction and novel view synthesis. Our system initializes camera poses using sparse visual odometry and obtains view-dependent dense geometry priors from a monocular depth prediction network. We harmonize the scale of poses and dense geometry, treating them as supervisory cues to train a neural implicit scene representation. NeRF-VO demonstrates exceptional performance in both photometric and geometric fidelity of the scene representation by jointly optimizing a sliding window of keyframed poses and the underlying dense geometry, which is accomplished through training the radiance field with volume rendering. We surpass state-of-the-art methods in pose estimation accuracy, novel view synthesis fidelity, and dense reconstruction quality across a variety of synthetic and real-world datasets, while achieving a higher camera tracking frequency and consuming less GPU memory.