Depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment. Deep learning algorithms for depth estimation have gained significant interest in recent years, owing to the potential benefits of this methodology in overcoming the limitations of active depth sensing systems. Moreover, due to the low cost and size of monocular cameras, researchers have focused their attention on monocular depth estimation (MDE), which consists in estimating a dense depth map from a single RGB video frame. State of the art MDE models typically rely on vision transformers (ViT) architectures that are highly deep and complex, making them unsuitable for fast inference on devices with hardware constraints. Purposely, in this paper, we address the problem of exploiting ViT in MDE on embedded devices. Those systems are usually characterized by limited memory capabilities and low-power CPU/GPU. We propose METER, a novel lightweight vision transformer architecture capable of achieving state of the art estimations and low latency inference performances on the considered embedded hardwares: NVIDIA Jetson TX1 and NVIDIA Jetson Nano. We provide a solution consisting of three alternative configurations of METER, a novel loss function to balance pixel estimation and reconstruction of image details, and a new data augmentation strategy to improve the overall final predictions. The proposed method outperforms previous lightweight works over the two benchmark datasets: the indoor NYU Depth v2 and the outdoor KITTI.
Samsung Research UK（三星英国研究院）；Centre for Research and Technology Hellas (CERTH)（希腊研究与技术中心）；Information Technologies Institute（信息技术研究所）
Monocular (relative or metric) depth estimation is a critical task for various applications, such as autonomous vehicles, augmented reality and image editing. In recent years, with the increasing availability of mobile devices, accurate and mobile-friendly depth models have gained importance. Increasingly accurate models typically require more computational resources, which inhibits the use of such models on mobile devices. The mobile use case is arguably the most unrestricted one, which requires highly accurate yet mobile-friendly architectures. Therefore, we try to answer the following quest…
Purdue University（普渡大学）；Rochester Institute of Technology（罗切斯特理工学院）
Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against learning-based MDE. In particular, we use an optimization-based method to systematically generate stealthy physical-object-oriented adversarial patches to attack depth estimation. We balance the stealth and effectiveness of our attack with object-oriented adversarial design, sensitive region localization, and natural style camouflage. Using real-world driving s…
Depth prediction is fundamental for many useful applications on computer vision and robotic systems. On mobile phones, the performance of some useful applications such as augmented reality, autofocus and so on could be enhanced by accurate depth prediction. In this work, an efficient fully convolutional network architecture for depth prediction has been proposed, which uses RegNetY 06 as the encoder and split-concatenate shuffle blocks as decoder. At the same time, an appropriate combination of data augmentation, hyper-parameters and loss functions to efficiently train the lightweight network …
NAVER LABS（NAVER实验室）；University of Maryland（马里兰大学）
Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with proprioceptive sensors. Such monocular SLAM systems can provide metrically scaled camera poses. Given these metric poses and monocular sequences, we propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation. Our approach is based on a teacher-student formulation which guides our netwo…
We present a generalised self-supervised learning approach for monocular estimation of the real depth across scenes with diverse depth ranges from 1--100s of meters. Existing supervised methods for monocular depth estimation require accurate depth measurements for training. This limitation has led to the introduction of self-supervised methods that are trained on stereo image pairs with a fixed camera baseline to estimate disparity which is transformed to depth given known calibration. Self-supervised approaches have demonstrated impressive results but do not generalise to scenes with differen…
We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot. Our system learns from conventional geometric SLAM, and outputs, using a single camera, the topological pose of the camera in an environment, and the depth map of obstacles around it. We use a CNN to localize in a topological map, and a conditional VAE to output depth for a camera image, conditional on this topological location estimation. We demonstrate the effectiveness of our monocular localization and depth estimation system on simulated and real datasets.
Korea Advanced Institute of Science and Technology（韩国高等科学技术研究院）
Unsupervised deep learning methods have shown promising performance for single-image depth estimation. Since most of these methods use binocular stereo pairs for self-supervision, the depth range is generally limited. Small-baseline stereo pairs provide small depth range but handle occlusions well. On the other hand, stereo images acquired with a wide-baseline rig cause occlusions-related errors in the near range but estimate depth well in the far range. In this work, we propose to integrate the advantages of the small and wide baselines. By training the network using three horizontally aligne…
Harbin Institute of Technology（哈尔滨工业大学）；University of Science and Technology of China（中国科学技术大学）
Monocular depth estimation is an essential task in the computer vision community. While tremendous successful methods have obtained excellent results, most of them are computationally expensive and not applicable for real-time on-device inference. In this paper, we aim to address more practical applications of monocular depth estimation, where the solution should consider not only the precision but also the inference time on mobile devices. To this end, we first develop an end-to-end learning-based model with a tiny weight size (1.4MB) and a short inference time (27FPS on Raspberry Pi 4). Then…
IIT Bombay（印度理工学院孟买分校）；MPI for Informatics, SIC（马克斯·普朗克信息学研究所，SIC）；IISc Bangalore（印度科学研究院班加罗尔）；Fast Code AI
This paper proposes GraviCap, i.e., a new approach for joint markerless 3D human motion capture and object trajectory estimation from monocular RGB videos. We focus on scenes with objects partially observed during a free flight. In contrast to existing monocular methods, we can recover scale, object trajectories as well as human bone lengths in meters and the ground plane's orientation, thanks to the awareness of the gravity constraining object motions. Our objective function is parametrised by the object's initial velocity and position, gravity direction and focal length, and jointly optimise…
Acquiring accurate three-dimensional depth information conventionally requires expensive multibeam LiDAR devices. Recently, researchers have developed a less expensive option by predicting depth information from two-dimensional color imagery. However, there still exists a substantial gap in accuracy between depth information estimated from two-dimensional images and real LiDAR point-cloud. In this paper, we introduce a fusion-based depth prediction method, called FusionMapping. This is the first method that fuses colored imagery and two-dimensional laser scan to estimate depth in-formation. Mo…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google Brain（谷歌大脑）
We present a novel approach for unsupervised learning of depth and ego-motion from monocular video. Unsupervised learning removes the need for separate supervisory signals (depth or ego-motion ground truth, or multi-view video). Prior work in unsupervised depth learning uses pixel-wise or gradient-based losses, which only consider pixels in small local neighborhoods. Our main contribution is to explicitly consider the inferred 3D geometry of the scene, enforcing consistency of the estimated 3D point clouds and ego-motion across consecutive frames. This is a challenging task and is solved by a …
We present an end-to-end neural network-based model for inferring an approximate 3D mesh representation of a human face from single camera input for AR applications. The relatively dense mesh model of 468 vertices is well-suited for face-based AR effects. The proposed model demonstrates super-realtime inference speed on mobile GPUs (100-1000+ FPS, depending on the device and model variant) and a high prediction quality that is comparable to the variance in manual annotations of the same image.
An active-learning framework for real-time depth perception from monocular vision streams
School of Mechanical and Automotive Engineering, Xiamen University of Technology（厦门理工学院机械与汽车工程学院）；Xiamen Innovative Centre for Automotive Electric Driving（厦门新能源汽车驱动创新中心）；King Long United Automotive Industry Co. Ltd.（金龙联合汽车工业有限公司）；School of Electrical and Electronic Engineering, The University of Adelaide（阿德莱德大学电气与电子工程学院）；School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）
In this paper, we present a fast monocular depth estimation method for enabling 3D perception capabilities of low-cost underwater robots. We formulate a novel end-to-end deep visual learning pipeline named UDepth, which incorporates domain knowledge of image formation characteristics of natural underwater scenes. First, we adapt a new input space from raw RGB image space by exploiting underwater light attenuation prior, and then devise a least-squared formulation for coarse pixel-wise depth prediction. Subsequently, we extend this into a domain projection loss that guides the end-to-end learni…
With the mass-market adoption of dual-camera mobile phones, leveraging stereo information in computer vision has become increasingly important. Current state-of-the-art methods utilize learning-based algorithms, where the amount and quality of training samples heavily influence results. Existing stereo image datasets are limited either in size or subject variety. Hence, algorithms trained on such datasets do not generalize well to scenarios encountered in mobile photography. We present Holopix50k, a novel in-the-wild stereo image dataset, comprising 49,368 image pairs contributed by users of t…
Zhejiang University（浙江大学）；Fuxi AI Lab, NetEase（网易伏羲人工智能实验室）
Self-supervised learning shows great potential in monoculardepth estimation, using image sequences as the only source ofsupervision. Although people try to use the high-resolutionimage for depth estimation, the accuracy of prediction hasnot been significantly improved. In this work, we find thecore reason comes from the inaccurate depth estimation inlarge gradient regions, making the bilinear interpolation er-ror gradually disappear as the resolution increases. To obtainmore accurate depth estimation in large gradient regions, itis necessary to obtain high-resolution features with spatialand s…
University of Portsmouth（朴茨茅斯大学）；Plymouth University（普利茅斯大学）
We tackle the problem of localizing an autonomous sea-surface vehicle in river estuarine areas using monocular camera and angular velocity input from an inertial sensor. Our method is challenged by two prominent drawbacks associated with the environment, which are typically not present in standard visual simultaneous localization and mapping (SLAM) applications on land (or air): a) Scene depth varies significantly (from a few meters to several kilometers) and, b) In conjunction to the latter, there exists no ground plane to provide features with enough disparity based on which to reliably dete…
Forest canopy height estimation from satellite RGB imagery using large-scale airborne LiDAR-derived training data and monocular depth estimation
Beijing Normal University（北京师范大学）；CSIRO Environment（英联邦科学与工业研究组织环境部）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Wuhan University（武汉大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）
Learning Vision-Based Omnidirectional Navigation: A Teacher-Student Approach Using Monocular Depth Estimation
Fraunhofer Institute for Material Flow and Logistics（弗劳恩霍夫材料流与物流研究所）；The Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能与机器学习研究所）
Monocular 3D object detection (Mono3D) in mobile settings (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Due to the near-far disparity phenomenon of monocular vision and the ever-changing camera pose, it is hard to acquire high detection accuracy, especially for far objects. Inspired by the insight that the depth of an object can be well determined according to the depth of the ground where it stands, in this paper, we propose a novel Mono3D framework, called MoGDE, which constantly estimates the corresponding ground depth of an image and then utilizes the esti…
Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo cam…
In this work, we propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence. Specifically, for 2D encoding, we propose lightweight yet effective stacked structures. Regarding 3D decoding, we provide an efficient graph operator, namely depth-separable spiral convolution. Moreover, we present a novel feature lifting module for bridging the gap between 2D and 3D representations. This module begins with a map-based position regression (MapReg) block to integrate the merits of both heatmap…
Centro de Informática, Universidade Federal de Pernambuco（伯南布哥联邦大学信息中心）
In the RoboCup Small Size League (SSL), teams are encouraged to propose solutions for executing basic soccer tasks inside the SSL field using only embedded sensing information. Thus, this work proposes an embedded monocular vision approach for detecting objects and estimating relative positions inside the soccer field. Prior knowledge from the environment is exploited by assuming objects lay on the ground, and the onboard camera has its position fixed on the robot. We implemented the proposed method on an NVIDIA Jetson Nano and employed SSD MobileNet v2 for 2D Object Detection with TensorRT op…
Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-d…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Human following on mobile robots has witnessed significant advances due to its potentials for real-world applications. Currently most human following systems are equipped with depth sensors to obtain distance information between human and robot, which suffer from the perception requirements and noises. In this paper, we design a wheeled mobile robot system with monocular pan-tilt camera to follow human, which can stay the target in the field of view and keep following simultaneously. The system consists of fast human detector, real-time and accurate visual tracker, and unified controller for m…
We present a direct method to calculate a 6DoF pose change of a monocular camera for mobile navigation. The calculated pose is estimated up to a constant unknown scale parameter that is kept constant over the entire reconstruction process. This method allows a direct cal- culation of the metric position and rotation without any necessity to fuse the information in a probabilistic approach over longer frame sequence as it is the case in most currently used VSLAM approaches. The algorithm provides two novel aspects to the field of monocular navigation. It allows a direct pose estimation without …
Mobile monocular 3D object detection (Mono3D) (e.g., on a vehicle, a drone, or a robot) is an important yet challenging task. Existing transformer-based offline Mono3D models adopt grid-based vision tokens, which is suboptimal when using coarse tokens due to the limited available computational power. In this paper, we propose an online Mono3D framework, called MonoATT, which leverages a novel vision transformer with heterogeneous tokens of varying shapes and sizes to facilitate mobile Mono3D. The core idea of MonoATT is to adaptively assign finer tokens to areas of more significance before uti…
Indian Institute of Technology, Kharagpur（印度理工学院卡拉格普尔分校）
We have developed an algorithm to generate a complete map of the traversable region for a personal assistant robot using monocular vision only. Using multiple taken by a simple webcam, obstacle detection and avoidance algorithms have been developed. Simple Linear Iterative Clustering (SLIC) has been used for segmentation to reduce the memory and computation cost. A simple mapping technique using inverse perspective mapping and occupancy grids, which is robust, and supports very fast updates has been used to create the map for indoor navigation.
In this paper, we tackle the problem of monocular bokeh synthesis, where we attempt to render a shallow depth of field image from a single all-in-focus image. Unlike in DSLR cameras, this effect can not be captured directly in mobile cameras due to the physical constraints of the mobile aperture. We thus propose a network-based approach that is capable of rendering realistic monocular bokeh from single image inputs. To do this, we introduce three new edge-aware Bokeh Losses based on a predicted monocular depth map, that sharpens the foreground edges while blurring the background. This model is…
Hong Kong University of Science and Technology（香港科技大学）；Tencent Inc（腾讯公司）
A monocular 3D object tracking system generally has only up-to-scale pose estimation results without any prior knowledge of the tracked object. In this paper, we propose a novel idea to recover the metric scale of an arbitrary dynamic object by optimizing the trajectory of the objects in the world frame, without motion assumptions. By introducing an additional constraint in the time domain, our monocular visual-inertial tracking system can obtain continuous six degree of freedom (6-DoF) pose estimation without scale ambiguity. Our method requires neither fixed multi-camera nor depth sensor set…
Hamilton Institute Maynooth University（汉密尔顿研究所梅努斯大学）；Valeo Vision Systems（法雷奥视觉系统公司）；Maynooth University（梅努斯大学）
Generating a detailed near-field perceptual model of the environment is an important and challenging problem in both self-driving vehicles and autonomous mobile robotics. A Bird Eye View (BEV) map, providing a panoptic representation, is a commonly used approach that provides a simplified 2D representation of the vehicle surroundings with accurate semantic level segmentation for many downstream tasks. Current state-of-the art approaches to generate BEV-maps employ a Convolutional Neural Network (CNN) backbone to create feature-maps which are passed through a spatial transformer to project the …
