Eye movement and strategic placement of the visual field onto the retina, gives animals increased resolution of the scene and suppresses distracting information. This fundamental system has been missing from video understanding with deep networks, typically limited to 224 by 224 pixel content locked to the camera frame. We propose a simple idea, WorldFeatures, where each feature at every layer has a spatial transformation, and the feature map is only transformed as needed. We show that a network built with these WorldFeatures, can be used to model eye movements, such as saccades, fixation, and smooth pursuit, even in a batch setting on pre-recorded video. That is, the network can for example use all 224 by 224 pixels to look at a small detail one moment, and the whole scene the next. We show that typical building blocks, such as convolutions and pooling, can be adapted to support WorldFeatures using available tools. Experiments are presented on the Charades, Olympic Sports, and Caltech-UCSD Birds-200-2011 datasets, exploring action recognition, fine-grained recognition, and video stabilization.
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
Active Multi-Object Tracking (AMOT) is a task where cameras are controlled by a centralized system to adjust their poses automatically and collaboratively so as to maximize the coverage of targets in their shared visual field. In AMOT, each camera only receives partial information from its observation, which may mislead cameras to take locally optimal action. Besides, the global goal, i.e., maximum coverage of objects, is hard to be directly optimized. To address the above issues, we propose a coordinate-aligned multi-camera collaboration system for AMOT. In our approach, we regard each camera…
Zenuity（泽纽伊提）；Chalmers University of Technology（查尔姆斯理工大学）
Monocular cameras are one of the most commonly used sensors in the automotive industry for autonomous vehicles. One major drawback using a monocular camera is that it only makes observations in the two dimensional image plane and can not directly measure the distance to objects. In this paper, we aim at filling this gap by developing a multi-object tracking algorithm that takes an image as input and produces trajectories of detected objects in a world coordinate system. We solve this by using a deep neural network trained to detect and estimate the distance to objects from a single input image…
In this paper, we propose a global method for estimating the motion of a camera which films a static scene. Our approach is direct, fast and robust, and deals with adjacent frames of a sequence. It is based on a quadratic approximation of the deformation between two images, in the case of a scene with constant depth in the camera coordinate system. This condition is very restrictive but we show that provided translation and depth inverse variations are small enough, the error on optical flow involved by the approximation of depths by a constant is small. In this context, we propose a new model…
Object tracking and localization is a complex task that typically requires processing power beyond the capabilities of low-power embedded cameras. This paper presents a new approach to real-time object tracking and localization using multi-view binary keypoints descriptor. The proposed approach offers a compromise between processing power, accuracy and networking bandwidth and has been tested using multiple distributed low-power smart cameras. Additionally, multiple optimization techniques are presented to improve the performance of the keypoints descriptor for low-power embedded systems.
Correspondences between 3D lines and their 2D images captured by a camera are often used to determine position and orientation of the camera in space. In this work, we propose a novel algebraic algorithm to estimate the camera pose. We parameterize 3D lines using Plücker coordinates that allow linear projection of the lines into the image. A line projection matrix is estimated using Linear Least Squares and the camera pose is then extracted from the matrix. An algebraic approach to handle mismatched line correspondences is also included. The proposed algorithm is an order of magnitude faster y…
Calibration in a multi camera network has widely been studied for over several years starting from the earlier days of photogrammetry. Many authors have presented several calibration algorithms with their relative advantages and disadvantages. In a stereovision system, multiple view reconstruction is a challenging task. However, the total computational procedure in detail has not been presented before. Here in this work, we are dealing with the problem that, when a world coordinate point is fixed in space, image coordinates of that 3D point vary for different camera positions and orientations.…
Paris Seine University（巴黎塞纳大学）；ENSEA（国立电子与应用技术学院）；CNRS（法国国家科学研究中心）；Samsung Research Institute（三星研究院）；Université Paris Saclay（巴黎萨克雷大学）；École des Ponts（巴黎高科路桥学校）
3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint. Alternatively, we propose a 3D human pose estimation method in camera coordinates, which allows effective combination of 2D annotated data and 3D poses and a straightforward multi-view generalization. To that end, we cast the problem as a view frustum space pose estimation, where absolute depth prediction and joint relative depth estimations are disentangled. Final 3D predictions are obtained in camera coordinates by the inverse camera projection. Based on this, we also present a con…
Image-based camera relocalization is an important problem in computer vision and robotics. Recent works utilize convolutional neural networks (CNNs) to regress for pixels in a query image their corresponding 3D world coordinates in the scene. The final pose is then solved via a RANSAC-based optimization scheme using the predicted coordinates. Usually, the CNN is trained with ground truth scene coordinates, but it has also been shown that the network can discover 3D scene geometry automatically by minimizing single-view reprojection loss. However, due to the deficiencies of the reprojection los…
Although the performance of 3D human pose and shape estimation methods has improved significantly in recent years, existing approaches typically generate 3D poses defined in camera or human-centered coordinate system. This makes it difficult to estimate a person's pure pose and motion in world coordinate system for a video captured using a moving camera. To address this issue, this paper presents a camera motion agnostic approach for predicting 3D human pose and mesh defined in the world coordinate system. The core idea of the proposed approach is to estimate the difference between two adjacen…
This paper presents an end-to-end neural mapping method for camera localization, dubbed NeuMap, encoding a whole scene into a grid of latent codes, with which a Transformer-based auto-decoder regresses 3D coordinates of query pixels. State-of-the-art feature matching methods require each scene to be stored as a 3D point cloud with per-point features, consuming several gigabytes of storage per scene. While compression is possible, performance drops significantly at high compression rates. Conversely, coordinate regression methods achieve high compression by storing scene information in a neural…
Simon Fraser University（西蒙菲莎大学）；Alibaba A.I Labs（阿里巴巴人工智能实验室）
Camera localization aims to estimate 6 DoF camera poses from RGB images. Traditional methods detect and match interest points between a query image and a pre-built 3D model. Recent learning-based approaches encode scene structures into a specific convolutional neural network (CNN) and thus are able to predict dense coordinates from RGB images. However, most of them require re-training or re-adaption for a new scene and have difficulties in handling large-scale scenes due to limited network capacity. We present a new method for scene agnostic camera localization using dense scene matching (DSM)…
University of Washington（华盛顿大学）；Zhejiang University（浙江大学）；Silkwave Holdings Limited（Silkwave控股有限公司）
Radar has long been a common sensor on autonomous vehicles for obstacle ranging and speed estimation. However, as a robust sensor to all-weather conditions, radar's capability has not been well-exploited, compared with camera or LiDAR. Instead of just serving as a supplementary sensor, radar's rich information hidden in the radio frequencies can potentially provide useful clues to achieve more complicated tasks, like object classification and detection. In this paper, we propose a new dataset, named CRUW, with a systematic annotator and performance evaluation system to address the radar object…
Rutgers University（罗格斯大学）；Toyota Motor North America（丰田汽车北美公司）
In Smart City and Vehicle-to-Everything (V2X) systems, acquiring pedestrians' accurate locations is crucial to traffic safety. Current systems adopt cameras and wireless sensors to detect and estimate people's locations via sensor fusion. Standard fusion algorithms, however, become inapplicable when multi-modal data is not associated. For example, pedestrians are out of the camera field of view, or data from camera modality is missing. To address this challenge and produce more accurate location estimations for pedestrians, we propose a Generative Adversarial Network (GAN) architecture. During…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Osaka University（大阪大学）；Kyoto University（京都大学）；RIKEN, Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also computationally inefficient due to the processing of point cloud data. In this work, we propose an effective and efficient approach at a low cost. First, we obtain panoramic videos with four normal cameras. Then, we transform human locations from a 2D panoramic image coordinate to a 3D panoramic camera coordinate using camera geometry and human bio-metric property (i.e., height). Finally, we generate 3D tracklets by…
TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments
Harbin Institute of Technology（哈尔滨工业大学）；Explore Academy of JD.com（京东探索研究院）；HiDream.ai Inc.（嗨创人工智能公司）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneously recognise surrounding objects and estimate 3D geometry. Such capabilities are crucial for computer vision guided systems which interact with the environment: autonomous driving, augmented reality and robotics. In particular, we propose a two step procedure. During the first step we train a convolutional neural network to jointly predict per-pixel globally unique instance la…
Scene coordinate regression has become an essential part of current camera re-localization methods. Different versions, such as regression forests and deep learning methods, have been successfully applied to estimate the corresponding camera pose given a single input image. In this work, we propose to regress the scene coordinates pixel-wise for a given RGB image by using deep learning. Compared to the recent methods, which usually employ RANSAC to obtain a robust pose estimate from the established point correspondences, we propose to regress confidences of these correspondences, which allows …
Nokia Bell Labs（诺基亚贝尔实验室）；New York University（纽约大学）
One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of monocular camera pose estimation via scene coordinate regression (SCR), we describe a novel method, Domain Adaptation of Networks for Camera pose Estimation (DANCE), which enables the training of models without access to any labels on the target task. DANCE requires unlabeled images (without known poses, ordering, or scene coordinate labels) and a 3D represen…
We propose a method to reconstruct global human trajectories from videos in the wild. Our optimization method decouples the camera and human motion, which allows us to place people in the same world coordinate frame. Most existing methods do not model the camera motion; methods that rely on the background pixels to infer 3D human motion usually require a full scene reconstruction, which is often not possible for in-the-wild videos. However, even when existing SLAM systems cannot recover accurate scene reconstructions, the background pixel motion still provides enough signal to constrain the ca…
Inria（法国国家信息与自动化研究所）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；University of Trento（特伦托大学）；University of Granada（格拉纳达大学）
In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video. Objects can be indistinctly located inside or outside the camera field of view. We refer to this problem as extended gaze following. The contributions of the paper are the followings. First, we propose a novel spatial representation of the gaze directions adopting a top-view perspective. Second, we develop several convolutional encoder/decoder networks to predict object locations and compare them with heuristics and…
Technical University of Munich（慕尼黑工业大学）；Chalmers University of Technology（查尔姆斯理工大学）；CIIRC, Czech Technical University in Prague（捷克布拉格捷克理工大学信息、机器人与控制研究所）；Five AI Ltd.（Five AI有限公司）；Google Inc.（谷歌公司）
Long-term camera re-localization is an important task with numerous computer vision and robotics applications. Whilst various outdoor benchmarks exist that target lighting, weather and seasonal changes, far less attention has been paid to appearance changes that occur indoors. This has led to a mismatch between popular indoor benchmarks, which focus on static scenes, and indoor environments that are of interest for many real-world applications. In this paper, we adapt 3RScan - a recently introduced indoor RGB-D dataset designed for object instance re-localization - to create RIO10, a new long-…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
Camera geo-localization from a monocular video is a fundamental task for video analysis and autonomous navigation. Although 3D reconstruction is a key technique to obtain camera poses, monocular 3D reconstruction in a large environment tends to result in the accumulation of errors in rotation, translation, and especially in scale: a problem known as scale drift. To overcome these errors, we propose a novel framework that integrates incremental structure from motion (SfM) and a scale drift correction method utilizing geo-tagged images, such as those provided by Google Street View. Our correctio…
Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality. Feed-forward absolute camera pose regression methods directly output poses by a network, but suffer from low accuracy. Meanwhile, scene coordinate based methods are accurate, but need iterative RANSAC post-processing, which brings challenges to efficient end-to-end training and inference. In order to have the best of both worlds, we propose a feed-forward method termed SC-wLS that exploits all scene coordinate estimates for weighted least squares pose …
Deep Learning for Camera Calibration and Beyond: A Survey
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Tampere University（坦佩雷大学）；School of Computer Science, Faculty of Engineering, The University of Sydney（悉尼大学工程学院计算机科学学院）
University of Oxford（牛津大学）；Technische Universität Dresden（德累斯顿工业大学）
This work addresses the task of camera localization in a known 3D scene given a single input RGB image. State-of-the-art approaches accomplish this in two steps: firstly, regressing for every pixel in the image its 3D scene coordinate and subsequently, using these coordinates to estimate the final 6D camera pose via RANSAC. To solve the first step, Random Forests (RFs) are typically used. On the other hand, Neural Networks (NNs) reign in many dense regression tasks, but are not test-time efficient. We ask the question: which of the two is best for camera localization? To address this, we make …
Depth sensing is a critical component of autonomous driving technologies, but today's LiDAR- or stereo camera-based solutions have limited range. We seek to increase the maximum range of self-driving vehicles' depth perception modules for the sake of better safety. To that end, we propose a novel three-camera system that utilizes small field of view cameras. Our system, along with our novel algorithm for computing metric depth, does not require full pre-calibration and can output dense depth maps with practically acceptable accuracy for scenes and objects at long distances not well covered by …
Beyond Reprojection Error: Camera Calibration with 3D Targets
Fraunhofer Institute for Computer Graphics Research（弗劳恩霍夫计算机图形研究所）；Technical University of Applied Sciences Würzburg-Schweinfurt（维尔茨堡-施韦因富特应用技术大学）；Technical University Darmstadt（达姆施塔特工业大学）
Cross-scene model adaption is crucial for camera relocalization in real scenarios. It is often preferable that a pre-learned model can be fast adapted to a novel scene with as few training samples as possible. The existing state-of-the-art approaches, however, can hardly support such few-shot scene adaption due to the entangling of image feature extraction and scene coordinate regression. To address this issue, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression, and pose estimation are performed separately. Our key insight is that featur…
Towards Effective Multi-Moving-Camera Tracking: A New Dataset and Lightweight Link Model
School of Computer Science and Technology, Donghua University（东华大学计算机科学与技术学院）；Institute of Integrated Science and Technology, Hosei University（法政大学综合科学技术研究所）；Frontiers Science Center for Intelligent Autonomous Systems, Tongji University（同济大学智能自主系统前沿科学中心）
Wuhan University（武汉大学）；NC State University（北卡罗来纳州立大学）
This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences. Our novel formulation poses some new challenges due to inevitable two-view and few-view configurations in the incremental SfM pipeline, which complicates the optimization of coordinate MLPs for volumetric neural rendering with unknown camera poses. Nevertheless, we demonstrate that the strong i…
In monocular 3D human pose estimation a common setup is to first detect 2D positions and then lift the detection into 3D coordinates. Many algorithms suffer from overfitting to camera positions in the training set. We propose a siamese architecture that learns a rotation equivariant hidden representation to reduce the need for data augmentation. Our method is evaluated on multiple databases with different base networks and shows a consistent improvement of error metrics. It achieves state-of-the-art cross-camera error rate among algorithms that use estimated 2D joint coordinates only.
Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Shanghai AI Lab（上海人工智能实验室）；SenseTime Research（商汤科技研究院）；Nanjing University（南京大学）；Tsinghua University（清华大学）
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Metric auto calibration of a camera network from multiple views has been reported by several authors. Resulting 3D reconstruction recovers shape faithfully, but not scale. However, preservation of scale becomes critical in applications, such as multi-party telepresence, where multiple 3D scenes need to be fused into a single coordinate system. In this context, we propose a camera network configuration that includes a stereo pair with known baseline separation, and analytically demonstrate Euclidean auto calibration of such network under mild conditions. Further, we experimentally validate our …
SGL: Structure Guidance Learning for Camera Localization
OPPO Research Institute（OPPO研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Wayz Intelligent Manufacturing Technology Co. Ltd.（维智智能制造科技有限公司）；Shanghai Jiao Tong University（上海交通大学）
We propose a learning-based method that solves monocular stereo and can be extended to fuse depth information from multiple target frames. Given two unconstrained images from a monocular camera with known intrinsic calibration, our network estimates relative camera poses and the depth map of the source image. The core contribution of the proposed method is threefold. First, a network is tailored for static scenes that jointly estimates the optical flow and camera motion. By the joint estimation, the optical flow search space is gradually reduced resulting in an efficient and accurate flow esti…
