We propose SF2SE3, a novel approach to estimate scene dynamics in form of a segmentation into independently moving rigid objects and their SE(3)-motions. SF2SE3 operates on two consecutive stereo or RGB-D images. First, noisy scene flow is obtained by application of existing optical flow and depth estimation algorithms. SF2SE3 then iteratively (1) samples pixel sets to compute SE(3)-motion proposals, and (2) selects the best SE(3)-motion proposal with respect to a maximum coverage formulation. Finally, objects are formed by assigning pixels uniquely to the selected SE(3)-motions based on consistency with the input scene flow and spatial proximity. The main novelties are a more informed strategy for the sampling of motion proposals and a maximum coverage formulation for the proposal selection. We conduct evaluations on multiple datasets regarding application of SF2SE3 for scene flow estimation, object segmentation and visual odometry. SF2SE3 performs on par with the state of the art for scene flow estimation and is more accurate for segmentation and odometry.
Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments. Semantic segmentation is largely used to discard dynamic associations before estimating camera motions but at the cost of discarding static features and is hard to scale up to unseen categories. In this paper, we leverage the mutual dependence between camera ego-motion and motion segmentation and show that both can be jointly refined in a single learning-based framework. In particular, we present DytanVO, the first supervised learning-based VO method that deals with dynamic environments. It takes two consecutive monocular frames in real-time and predicts camera ego-motion in an iterative fashion. Our method achieves an average improvement of 27.7% in ATE over state-of-the-art VO solutions in real-world dynamic environments, and even performs competitively among dynamic visual SLAM systems which optimize the trajectory on the backend. Experiments on plentiful unseen environments also demonstrate our method's generalizability.
We present the ALTO dataset, a vision-focused dataset for the development and benchmarking of Visual Place Recognition and Localization methods for Unmanned Aerial Vehicles. The dataset is composed of two long (approximately 150km and 260km) trajectories flown by a helicopter over Ohio and Pennsylvania, and it includes high precision GPS-INS ground truth location data, high precision accelerometer readings, laser altimeter readings, and RGB downward facing camera imagery. In addition, we provide reference imagery over the flight paths, which makes this dataset suitable for VPR benchmarking and other tasks common in Localization, such as image registration and visual odometry. To the author's knowledge, this is the largest real-world aerial-vehicle dataset of this kind. Our dataset is available at https://github.com/MetaSLAM/ALTO.
Depth estimation, visual odometry (VO), and bird's-eye-view (BEV) scene layout estimation present three critical tasks for driving scene perception, which is fundamental for motion planning and navigation in autonomous driving. Though they are complementary to each other, prior works usually focus on each individual task and rarely deal with all three tasks together. A naive way is to accomplish them independently in a sequential or parallel manner, but there are many drawbacks, i.e., 1) the depth and VO results suffer from the inherent scale ambiguity issue; 2) the BEV layout is directly predicted from the front-view image without using any depth-related information, although the depth map contains useful geometry clues for inferring scene layouts. In this paper, we address these issues by proposing a novel joint perception framework named JPerceiver, which can simultaneously estimate scale-aware depth and VO as well as BEV layout from a monocular video sequence. It exploits the cross-view geometric transformation (CGT) to propagate the absolute scale from the road layout to depth and VO based on a carefully-designed scale loss. Meanwhile, a cross-view and cross-modal transfer (CCT) module is devised to leverage the depth clues for reasoning road and vehicle layout through an attention mechanism. JPerceiver can be trained in an end-to-end multi-task learning way, where the CGT scale loss and CCT module promote inter-task knowledge transfer to benefit feature learning of each task. Experiments on Argoverse, Nuscenes and KITTI show the superiority of JPerceiver over existing methods on all the above three tasks in terms of accuracy, model size, and inference speed. The code and models are available at~\href{https://github.com/sunnyHelen/JPerceiver}{https://github.com/sunnyHelen/JPerceiver}.
Deep neural networks are known to be susceptible to adversarial perturbations -- small perturbations that alter the output of the network and exist under strict norm limitations. While such perturbations are usually discussed as tailored to a specific input, a universal perturbation can be constructed to alter the model's output on a set of inputs. Universal perturbations present a more realistic case of adversarial attacks, as awareness of the model's exact input is not required. In addition, the universal attack setting raises the subject of generalization to unseen data, where given a set of inputs, the universal perturbations aim to alter the model's output on out-of-sample data. In this work, we study physical passive patch adversarial attacks on visual odometry-based autonomous navigation systems. A visual odometry system aims to infer the relative camera motion between two corresponding viewpoints, and is frequently used by vision-based autonomous navigation systems to estimate their state. For such navigation systems, a patch adversarial perturbation poses a severe security issue, as it can be used to mislead a system onto some collision course. To the best of our knowledge, we show for the first time that the error margin of a visual odometry model can be significantly increased by deploying patch adversarial attacks in the scene. We provide evaluation on synthetic closed-loop drone navigation data and demonstrate that a comparable vulnerability exists in real data. A reference implementation of the proposed method and the reported experiments is provided at https://github.com/patchadversarialattacks/patchadversarialattacks.
We present PVO, a novel panoptic visual odometry framework to achieve more comprehensive modeling of the scene motion, geometry, and panoptic segmentation information. Our PVO models visual odometry (VO) and video panoptic segmentation (VPS) in a unified view, which makes the two tasks mutually beneficial. Specifically, we introduce a panoptic update module into the VO Module with the guidance of image panoptic segmentation. This Panoptic-Enhanced VO Module can alleviate the impact of dynamic objects in the camera pose estimation with a panoptic-aware dynamic mask. On the other hand, the VO-Enhanced VPS Module also improves the segmentation accuracy by fusing the panoptic segmentation result of the current frame on the fly to the adjacent frames, using geometric information such as camera pose, depth, and optical flow obtained from the VO Module. These two modules contribute to each other through recurrent iterative optimization. Extensive experiments demonstrate that PVO outperforms state-of-the-art methods in both visual odometry and video panoptic segmentation tasks.
Can an autonomous agent navigate in a new environment without building an explicit map? For the task of PointGoal navigation ('Go to $\Delta x$, $\Delta y$') under idealized settings (no RGB-D and actuation noise, perfect GPS+Compass), the answer is a clear 'yes' - map-less neural models composed of task-agnostic components (CNNs and RNNs) trained with large-scale reinforcement learning achieve 100% Success on a standard dataset (Gibson). However, for PointNav in a realistic setting (RGB-D and actuation noise, no GPS+Compass), this is an open question; one we tackle in this paper. The strongest published result for this task is 71.7% Success. First, we identify the main (perhaps, only) cause of the drop in performance: the absence of GPS+Compass. An agent with perfect GPS+Compass faced with RGB-D sensing and actuation noise achieves 99.8% Success (Gibson-v2 val). This suggests that (to paraphrase a meme) robust visual odometry is all we need for realistic PointNav; if we can achieve that, we can ignore the sensing and actuation noise. With that as our operating hypothesis, we scale the dataset and model size, and develop human-annotation-free data-augmentation techniques to train models for visual odometry. We advance the state of art on the Habitat Realistic PointNav Challenge from 71% to 94% Success (+23, 31% relative) and 53% to 74% SPL (+21, 40% relative). While our approach does not saturate or 'solve' this dataset, this strong improvement combined with promising zero-shot sim2real transfer (to a LoCoBot) provides evidence consistent with the hypothesis that explicit mapping may not be necessary for navigation, even in a realistic setting.
Visual-inertial-odometry has attracted extensive attention in the field of autonomous driving and robotics. The size of Field of View (FoV) plays an important role in Visual-Odometry (VO) and Visual-Inertial-Odometry (VIO), as a large FoV enables to perceive a wide range of surrounding scene elements and features. However, when the field of the camera reaches the negative half plane, one cannot simply use [u,v,1]^T to represent the image feature points anymore. To tackle this issue, we propose LF-VIO, a real-time VIO framework for cameras with extremely large FoV. We leverage a three-dimensional vector with unit length to represent feature points, and design a series of algorithms to overcome this challenge. To address the scarcity of panoramic visual odometry datasets with ground-truth location and pose, we present the PALVIO dataset, collected with a Panoramic Annular Lens (PAL) system with an entire FoV of 360{\deg}x(40{\deg}-120{\deg}) and an IMU sensor. With a comprehensive variety of experiments, the proposed LF-VIO is verified on both the established PALVIO benchmark and a public fisheye camera dataset with a FoV of 360{\deg}x(0{\deg}-93.5{\deg}). LF-VIO outperforms state-of-the-art visual-inertial-odometry methods. Our dataset and code are made publicly available at https://github.com/flysoaryun/LF-VIO
Safe deployment of self-driving cars (SDC) necessitates thorough simulated and in-field testing. Most testing techniques consider virtualized SDCs within a simulation environment, whereas less effort has been directed towards assessing whether such techniques transfer to and are effective with a physical real-world vehicle. In this paper, we shed light on the problem of generalizing testing results obtained in a driving simulator to a physical platform and provide a characterization and quantification of the sim2real gap affecting SDC testing. In our empirical study, we compare SDC testing when deployed on a physical small-scale vehicle vs its digital twin. Due to the unavailability of driving quality indicators from the physical platform, we use neural rendering to estimate them through visual odometry, hence allowing full comparability with the digital twin. Then, we investigate the transferability of behavior and failure exposure between virtual and real-world environments, targeting both unintended abnormal test data and intended adversarial examples. Our study shows that, despite the usage of a faithful digital twin, there are still critical shortcomings that contribute to the reality gap between the virtual and physical world, threatening existing testing solutions that only consider virtual SDCs. On the positive side, our results present the test configurations for which physical testing can be avoided, either because their outcome does transfer between virtual and physical environments, or because the uncertainty profiles in the simulator can help predict their outcome in the real world.
We present 360-DFPE, a sequential floor plan estimation method that directly takes 360-images as input without relying on active sensors or 3D information. Our approach leverages a loosely coupled integration between a monocular visual SLAM solution and a monocular 360-room layout approach, which estimate camera poses and layout geometries, respectively. Since our task is to sequentially capture the floor plan using monocular images, the entire scene structure, room instances, and room shapes are unknown. To tackle these challenges, we first handle the scale difference between visual odometry and layout geometry via formulating an entropy minimization process, which enables us to directly align 360-layouts without knowing the entire scene in advance. Second, to sequentially identify individual rooms, we propose a novel room identification algorithm that tracks every room along the camera exploration using geometry information. Lastly, to estimate the final shape of the room, we propose a shortest path algorithm with an iterative coarse-to-fine strategy, which improves prior formulations with higher accuracy and faster run-time. Moreover, we collect a new floor plan dataset with challenging large-scale scenes, providing both point clouds and sequential 360-image information. Experimental results show that our monocular solution achieves favorable performance against the current state-of-the-art algorithms that rely on active sensors and require the entire scene reconstruction data in advance.
In this paper, we present TANDEM a real-time monocular tracking and dense mapping framework. For pose estimation, TANDEM performs photometric bundle adjustment based on a sliding window of keyframes. To increase the robustness, we propose a novel tracking front-end that performs dense direct image alignment using depth maps rendered from a global model that is built incrementally from dense depth predictions. To predict the dense depth maps, we propose Cascade View-Aggregation MVSNet (CVA-MVSNet) that utilizes the entire active keyframe window by hierarchically constructing 3D cost volumes with adaptive view aggregation to balance the different stereo baselines between the keyframes. Finally, the predicted depth maps are fused into a consistent global map represented as a truncated signed distance function (TSDF) voxel grid. Our experimental results show that TANDEM outperforms other state-of-the-art traditional and learning-based monocular visual odometry (VO) methods in terms of camera tracking. Moreover, TANDEM shows state-of-the-art real-time 3D reconstruction performance.
We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use an appropriate motion model that can help existing self-supervised monocular VO (SSM-VO) algorithms to overcome issues related to the local minima within their self-supervised loss functions. The motion model is expressed with a neural network named PPnet. It is trained to coarsely predict the next pose of the camera and the uncertainty of this prediction. Our self-supervised approach combines the original loss and the motion loss, which is the weighted difference between the prediction and the generated ego-motion. Taking two existing SSM-VO systems as our baseline, we evaluate our MotionHint algorithm on the standard KITTI benchmark. Experimental results show that our MotionHint algorithm can be easily applied to existing open-sourced state-of-the-art SSM-VO systems to greatly improve the performance by reducing the resulting ATE by up to 28.73%.
In the future, extraterrestrial expeditions will not only be conducted by rovers but also by flying robots. The technical demonstration drone Ingenuity, that just landed on Mars, will mark the beginning of a new era of exploration unhindered by terrain traversability. Robust self-localization is crucial for that. Cameras that are lightweight, cheap and information-rich sensors are already used to estimate the ego-motion of vehicles. However, methods proven to work in man-made environments cannot simply be deployed on other planets. The highly repetitive textures present in the wastelands of Mars pose a huge challenge to descriptor matching based approaches. In this paper, we present an advanced robust monocular odometry algorithm that uses efficient optical flow tracking to obtain feature correspondences between images and a refined keyframe selection criterion. In contrast to most other approaches, our framework can also handle rotation-only motions that are particularly challenging for monocular odometry systems. Furthermore, we present a novel approach to estimate the current risk of scale drift based on a principal component analysis of the relative translation information matrix. This way we obtain an implicit measure of uncertainty. We evaluate the validity of our approach on all sequences of a challenging real-world dataset captured in a Mars-like environment and show that it outperforms state-of-the-art approaches.
Over the last decade, one of the most relevant public datasets for evaluating odometry accuracy is the KITTI dataset. Beside the quality and rich sensor setup, its success is also due to the online evaluation tool, which enables researchers to benchmark and compare algorithms. The results are evaluated on the test subset solely, without any knowledge about the ground truth, yielding unbiased, overfit free and therefore relevant validation for robot localization based on cameras, 3D laser or combination of both. However, as any sensor setup, it requires prior calibration and rectified stereo images are provided, introducing dependence on the default calibration parameters. Given that, a natural question arises if a better set of calibration parameters can be found that would yield higher odometry accuracy. In this paper, we propose a new approach for one shot calibration of the KITTI dataset multiple camera setup. The approach yields better calibration parameters, both in the sense of lower calibration reprojection errors and lower visual odometry error. We conducted experiments where we show for three different odometry algorithms, namely SOFT2, ORB-SLAM2 and VISO2, that odometry accuracy is significantly improved with the proposed calibration parameters. Moreover, our odometry, SOFT2, in conjunction with the proposed calibration method achieved the highest accuracy on the official KITTI scoreboard with 0.53% translational and 0.0009 deg/m rotational error, outperforming even 3D laser-based methods.
Mobile AR applications benefit from fast initialization to display world-locked effects instantly. However, standard visual odometry or SLAM algorithms require motion parallax to initialize (see Figure 1) and, therefore, suffer from delayed initialization. In this paper, we present a 6-DoF monocular visual odometry that initializes instantly and without motion parallax. Our main contribution is a pose estimator that decouples estimating the 5-DoF relative rotation and translation direction from the 1-DoF translation magnitude. While scale is not observable in a monocular vision-only setting, it is still paramount to estimate a consistent scale over the whole trajectory (even if not physically accurate) to avoid AR effects moving erroneously along depth. In our approach, we leverage the fact that depth errors are not perceivable to the user during rotation-only motion. However, as the user starts translating the device, depth becomes perceivable and so does the capability to estimate consistent scale. Our proposed algorithm naturally transitions between these two modes. We perform extensive validations of our contributions with both a publicly available dataset and synthetic data. We show that the proposed pose estimator outperforms the classical approaches for 6-DoF pose estimation used in the literature in low-parallax configurations. We release a dataset for the relative pose problem using real data to facilitate the comparison with future solutions for the relative pose problem. Our solution is either used as a full odometry or as a preSLAM component of any supported SLAM system (ARKit, ARCore) in world-locked AR effects on platforms such as Instagram and Facebook.
We present a dense-indirect SLAM system using external dense optical flows as input. We extend the recent probabilistic visual odometry model VOLDOR [Min et al. CVPR'20], by incorporating the use of geometric priors to 1) robustly bootstrap estimation from monocular capture, while 2) seamlessly supporting stereo and/or RGB-D input imagery. Our customized back-end tightly couples our intermediate geometric estimates with an adaptive priority scheme managing the connectivity of an incremental pose graph. We leverage recent advances in dense optical flow methods to achieve accurate and robust camera pose estimates, while constructing fine-grain globally-consistent dense environmental maps. Our open source implementation [https://github.com/htkseason/VOLDOR] operates online at around 15 FPS on a single GTX1080Ti GPU.
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-logistic distribution model. Moreover, the log-logistic residual model generalizes well to different state-of-the-art optical flow methods, making our approach modular and agnostic to the choice of optical flow estimators. Our method achieved top-ranking results on both TUM RGB-D and KITTI odometry benchmarks. Our open-sourced implementation is inherently GPU-friendly with only linear computational and storage growth.
A useful application of event sensing is visual odometry, especially in settings that require high-temporal resolution. The state-of-the-art method of contrast maximisation recovers the motion from a batch of events by maximising the contrast of the image of warped events. However, the cost scales with image resolution and the temporal resolution can be limited by the need for large batch sizes to yield sufficient structure in the contrast image. In this work, we propose spatiotemporal registration as a compelling technique for event-based rotational motion estimation. We theoretcally justify the approach and establish its fundamental and practical advantages over contrast maximisation. In particular, spatiotemporal registration also produces feature tracks as a by-product, which directly supports an efficient visual odometry pipeline with graph-based optimisation for motion averaging. The simplicity of our visual odometry pipeline allows it to process more than 1 M events/second. We also contribute a new event dataset for visual odometry, where motion sequences with large velocity variations were acquired using a high-precision robot arm.
Multi-view geometry-based methods dominate the last few decades in monocular Visual Odometry for their superior performance, while they have been vulnerable to dynamic and low-texture scenes. More importantly, monocular methods suffer from scale-drift issue, i.e., errors accumulate over time. Recent studies show that deep neural networks can learn scene depths and relative camera in a self-supervised manner without acquiring ground truth labels. More surprisingly, they show that the well-trained networks enable scale-consistent predictions over long videos, while the accuracy is still inferior to traditional methods because of ignoring geometric information. Building on top of recent progress in computer vision, we design a simple yet robust VO system by integrating multi-view geometry and deep learning on Depth and optical Flow, namely DF-VO. In this work, a) we propose a method to carefully sample high-quality correspondences from deep flows and recover accurate camera poses with a geometric module; b) we address the scale-drift issue by aligning geometrically triangulated depths to the scale-consistent deep depths, where the dynamic scenes are taken into account. Comprehensive ablation studies show the effectiveness of the proposed method, and extensive evaluation results show the state-of-the-art performance of our system, e.g., Ours (1.652%) v.s. ORB-SLAM (3.247%}) in terms of translation error in KITTI Odometry benchmark. Source code is publicly available at: \href{https://github.com/Huangying-Zhan/DF-VO}{DF-VO}.
Surround View fisheye cameras are commonly deployed in automated driving for 360\deg{} near-field sensing around the vehicle. This work presents a multi-task visual perception network on unrectified fisheye images to enable the vehicle to sense its surrounding environment. It consists of six primary tasks necessary for an autonomous driving system: depth estimation, visual odometry, semantic segmentation, motion segmentation, object detection, and lens soiling detection. We demonstrate that the jointly trained model performs better than the respective single task versions. Our multi-task model has a shared encoder providing a significant computational advantage and has synergized decoders where tasks support each other. We propose a novel camera geometry based adaptation mechanism to encode the fisheye distortion model both at training and inference. This was crucial to enable training on the WoodScape dataset, comprised of data from different parts of the world collected by 12 different cameras mounted on three different cars with different intrinsics and viewpoints. Given that bounding boxes is not a good representation for distorted fisheye images, we also extend object detection to use a polygon with non-uniformly sampled vertices. We additionally evaluate our model on standard automotive datasets, namely KITTI and Cityscapes. We obtain the state-of-the-art results on KITTI for depth estimation and pose estimation tasks and competitive performance on the other tasks. We perform extensive ablation studies on various architecture choices and task weighting methodologies. A short video at https://youtu.be/xbSjZ5OfPes provides qualitative results.