Given an image sequence featuring a portion of a sports field filmed by a moving and uncalibrated camera, such as the one of the smartphones, our goal is to compute automatically in real time the focal length and extrinsic camera parameters for each image in the sequence without using a priori knowledges of the position and orientation of the camera. To this end, we propose a novel framework that combines accurate localization and robust identification of specific keypoints in the image by using a fully convolutional deep architecture. Our algorithm exploits both the field lines and the players' image locations, assuming their ground plane positions to be given, to achieve accuracy and robustness that is beyond the current state of the art. We will demonstrate its effectiveness on challenging soccer, basketball, and volleyball benchmark datasets.
L3S Research Center（L3S研究中心）；Leibniz University Hannover（汉诺威莱布尼茨大学）；TIB – Leibniz Information Centre for Science and Technology（莱布尼茨科学技术信息中心）
Sports field registration in broadcast videos is typically interpreted as the task of homography estimation, which provides a mapping between a planar field and the corresponding visible area of the image. In contrast to previous approaches, we consider the task as a camera calibration problem. First, we introduce a differentiable objective function that is able to learn the camera pose and focal length from segment correspondences (e.g., lines, point clouds), based on pixel-level annotations for segments of a known calibration object. The calibration module iteratively minimizes the segment r…
University of British Columbia（不列颠哥伦比亚大学）；Zhejiang University（浙江大学）
We present an online SLAM system specifically designed to track pan-tilt-zoom (PTZ) cameras in highly dynamic sports such as basketball and soccer games. In these games, PTZ cameras rotate very fast and players cover large image areas. To overcome these challenges, we propose to use a novel camera model for tracking and to use rays as landmarks in mapping. Rays overcome the missing depth in pure-rotation cameras. We also develop an online pan-tilt forest for mapping and introduce moving objects (players) detection to mitigate negative impacts from foreground objects. We test our method on both…
Time-Archival Camera Virtualization for Sports and Visual Performances
Spatial AI Lab, Visual Computing \& Computational Media (VCCM) Section；organization= College of Performance, Visualization；organization= Department of Electrical；organization= Department of Computer Science；organization= Texas A\&M University , city= College Station , state= Texas , country= USA
Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for testing examples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we introduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consistent manner. Second, we…
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…
York University（约克大学）；University of Manitoba（曼尼托巴大学）；Ryerson University（瑞尔森大学）
We consider the problem of unsupervised camera pose estimation. Given an input video sequence, our goal is to estimate the camera pose (i.e. the camera motion) between consecutive frames. Traditionally, this problem is tackled by placing strict constraints on the transformation vector or by incorporating optical flow through a complex pipeline. We propose an alternative approach that utilizes a compositional re-estimation process for camera pose estimation. Given an input, we first estimate a depth map. Our method then iteratively estimates the camera motion based on the estimated depth map. O…
Maria Curie-Sklodowska University（玛丽亚·居里-斯克沃多夫斯卡大学）；Warsaw University of Technology（华沙理工大学）
In this paper a method for camera pose estimation from a sequence of images is presented. The method assumes camera is calibrated (intrinsic parameters are known) which allows to decrease a number of required pairs of corresponding points compared to uncalibrated case. Our algorithm can be used as a first stage in a structure from motion stereo reconstruction system.
Shandong University（山东大学）；Peking University（北京大学）；Tencent AI Lab（腾讯人工智能实验室）；Stanford University（斯坦福大学）；vjia（3vjia）
In this work, we tackle the problem of active camera localization, which controls the camera movements actively to achieve an accurate camera pose. The past solutions are mostly based on Markov Localization, which reduces the position-wise camera uncertainty for localization. These approaches localize the camera in the discrete pose space and are agnostic to the localization-driven scene property, which restricts the camera pose accuracy in the coarse scale. We propose to overcome these limitations via a novel active camera localization algorithm, composed of a passive and an active localizati…
Camera pose estimation or camera relocalization is the centerpiece in numerous computer vision tasks such as visual odometry, structure from motion (SfM) and SLAM. In this paper we propose a neural network approach with a graph transformer backbone, namely TransCamP, to address the camera relocalization problem. In contrast with prior work where the pose regression is mainly guided by photometric consistency, TransCamP effectively fuses the image features, camera pose information and inter-frame relative camera motions into encoded graph attributes and is trained towards the graph consistency …
Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）；ShanghaiTech University（上海科技大学）；University of California, San Diego（加州大学圣迭戈分校）
We introduce GNeRF, a framework to marry Generative Adversarial Networks (GAN) with Neural Radiance Field (NeRF) reconstruction for the complex scenarios with unknown and even randomly initialized camera poses. Recent NeRF-based advances have gained popularity for remarkable realistic novel view synthesis. However, most of them heavily rely on accurate camera poses estimation, while few recent methods can only optimize the unknown camera poses in roughly forward-facing scenes with relatively short camera trajectories and require rough camera poses initialization. Differently, our GNeRF only ut…
University of Toronto（多伦多大学）；Carnegie Mellon University（卡内基梅隆大学）；Simon Fraser University（西蒙弗雷泽大学）；Google（谷歌）；Vector Institute（向量研究所）
Camera pose estimation is a key step in standard 3D reconstruction pipelines that operate on a dense set of images of a single object or scene. However, methods for pose estimation often fail when only a few images are available because they rely on the ability to robustly identify and match visual features between image pairs. While these methods can work robustly with dense camera views, capturing a large set of images can be time-consuming or impractical. We propose SparsePose for recovering accurate camera poses given a sparse set of wide-baseline images (fewer than 10). The method learns …
Xiangtan University（湘潭大学）；Central South University（中南大学）
The neural radiance field (NeRF) for realistic novel view synthesis requires camera poses to be pre-acquired by a structure-from-motion (SfM) approach. This two-stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis. We integrate the pose extraction and view synthesis into a single end-to-end procedure so they can benefit from each other. For training NeRF models, only RGB images are given, without pre-known camera poses. The camera poses are obtained by the epipolar constraint in which the identical fea…
Centre for Mathematical Sciences（数学科学中心）；Lund University（隆德大学）
In this paper we present a fast minimal solver for absolute camera pose estimation from four known points that lie in a plane. We assume a perspective camera model with unknown focal length and unknown radial distortion. The radial distortion is modelled using the division model with one parameter. We show that the solutions to this problem can be found from a univariate six-degree polynomial. This results in a very fast and numerically stable solver.
We consider the task of re-calibrating the 3D pose of a static surveillance camera, whose pose may change due to external forces, such as birds, wind, falling objects or earthquakes. Conventionally, camera pose estimation can be solved with a PnP (Perspective-n-Point) method using 2D-to-3D feature correspondences, when 3D points are known. However, 3D point annotations are not always available or practical to obtain in real-world applications. We propose an alternative strategy for extracting 3D information to solve for camera pose by using pedestrian trajectories. We observe that 2D pedestria…
RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories
School of Geodesy and Geomatics, Wuhan University（武汉大学测绘学院）；Department of Computer Science and Technology, HIT (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术系）；XGRIDS；Department of Computer Science, HKBU（香港大学计算机科学系）；Department of Computer Science and Engineering, HKUST（香港理工大学计算机科学与工程系）；Data Science and Analytics Thrust, HKUST (Guangzhou)（香港理工大学数据科学与分析方向）
Calibrating sports cameras is important for autonomous broadcasting and sports analysis. Here we propose a highly automatic method for calibrating sports cameras from a single image using synthetic data. First, we develop a novel camera pose engine. The camera pose engine has only three significant free parameters so that it can effectively generate a lot of camera poses and corresponding edge (i.e, field marking) images. Then, we learn compact deep features via a siamese network from paired edge image and camera pose and build a feature-pose database. After that, we use a novel two-GAN (gener…
SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding
School of Information Science and Engineering, Yunnan University（云南大学信息科学与工程学院）；Yunnan University（云南大学）；School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）；Yunnan Key Laboratory of Intelligent Systems and Computing（智能系统与计算重点实验室）
CaLDiff: Camera Localization in NeRF via Pose Diffusion
NepAl Applied Mathematics and Informatics Institute for research (NAAMII)（尼泊尔应用数学与信息学研究所）；ETH Zürich（苏黎世联邦理工学院）；State University of New York (SUNY) at Korea（纽约州立大学韩国分校）
Over the last two decades, deep learning has transformed the field of computer vision. Deep convolutional networks were successfully applied to learn different vision tasks such as image classification, image segmentation, object detection and many more. By transferring the knowledge learned by deep models on large generic datasets, researchers were further able to create fine-tuned models for other more specific tasks. Recently this idea was applied for regressing the absolute camera pose from an RGB image. Although the resulting accuracy was sub-optimal, compared to classic feature-based sol…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；TianJin Intelligent Tech.Institute of CASIA Co. ,Ltd（中科智能（天津）科技研究院有限公司）
Accurate camera pose estimation result is essential for visual SLAM (VSLAM). This paper presents a novel pose correction method to improve the accuracy of the VSLAM system. Firstly, the relationship between the camera pose estimation error and bias values of map points is derived based on the optimized function in VSLAM. Secondly, the bias value of the map point is calculated by a statistical method. Finally, the camera pose estimation error is compensated according to the first derived relationship. After the pose correction, procedures of the original system, such as the bundle adjustment (B…
Beijing University of Posts and Telecommunications（北京邮电大学）
It is an exciting task to recover the scene's 3d-structure and camera pose from the video sequence. Most of the current solutions divide it into two parts, monocular depth recovery and camera pose estimation. The monocular depth recovery is often studied as an independent part, and a better depth estimation is used to solve the pose. While camera pose is still estimated by traditional SLAM (Simultaneous Localization And Mapping) methods in most cases. The use of unsupervised method for monocular depth recovery and pose estimation has benefited from the study of [1] and achieved good results. I…
We propose a novel camera pose estimation or perspective-n-point (PnP) algorithm, based on the idea of consistency regions and half-space intersections. Our algorithm has linear time-complexity and a squared reconstruction error that decreases at least quadratically, as the number of feature point correspondences increase. Inspired by ideas from triangulation and frame quantisation theory, we define consistent reconstruction and then present SHAPE, our proposed consistent pose estimation algorithm. We compare this algorithm with state-of-the-art pose estimation techniques in terms of accuracy …
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…
MultiCam: On-the-fly Multi-Camera Pose Estimation Using Spatiotemporal Overlaps of Known Objects
Human-Centered-Computing and Extended Reality Lab（以人为本计算与扩展现实实验室）；Klinikum rechts der Isar（右岸诊所）；Orthopedics and Sports Orthopedics（骨科和运动骨科）；Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所（MIRMI））；TH Köln（科隆大学）；Computer Graphics Group（计算机图形学组）；Photogrammetry and Remote Sensing Lab（摄影测量与遥感实验室）
Inria（法国国家信息与自动化研究所）；Université de Lorraine（洛林大学）；LORIA（洛林计算机科学及其应用实验室）；CNRS（法国国家科学研究中心）
In this paper, we propose an object-based camera pose estimation from a single RGB image and a pre-built map of objects, represented with ellipsoidal models. We show that contrary to point correspondences, the definition of a cost function characterizing the projection of a 3D object onto a 2D object detection is not straightforward. We develop an ellipse-ellipse cost based on level sets sampling, demonstrate its nice properties for handling partially visible objects and compare its performance with other common metrics. Finally, we show that the use of a predictive uncertainty on the detected…
In real-world applications the Perspective-n-Point (PnP) problem should generally be applied in a sequence of images which a set of drift-prone features are tracked over time. In this paper, we consider both the temporal dependency of camera poses and the uncertainty of features for the sequential camera pose estimation. Using the Extended Kalman Filter (EKF), a priori estimate of the camera pose is calculated from the camera motion model and then corrected by minimizing the reprojection error of the reference points. Experimental results, using both simulated and real data, demonstrate that t…
NTT DOCOMO（日本电信电话多科莫公司）；The University of Tokyo（东京大学）
Although many studies have investigated markerless motion capture, the technology has not been applied to real sports or concerts. In this paper, we propose a markerless motion capture method with spatiotemporal accuracy and smoothness from multiple cameras in wide-space and multi-person environments. The proposed method predicts each person's 3D pose and determines the bounding box of multi-camera images small enough. This prediction and spatiotemporal filtering based on human skeletal model enables 3D reconstruction of the person and demonstrates high-accuracy. The accurate 3D reconstruction…
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose. End-to-end learning circumvents pose, but requires more labels to generalize. We introduce Video Pose Distillation (VPD), a weakly-supervised technique to learn features for new video domains, such as individual sports that challenge pose estimation. Under VPD, a student network learns to…
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）
This paper presents a generic 6DOF camera pose estimation method, which can be used for both the pinhole camera and the fish-eye camera. Different from existing methods, relative positions of 3D points rather than absolute coordinates in the world coordinate system are employed in our method, and it has a unique solution. The application scope of POSIT (Pose from Orthography and Scaling with Iteration) algorithm is generalized to fish-eye cameras by combining with the radially symmetric projection model. The image point relationship between the pinhole camera and the fish-eye camera is derived…
RFA Engineering（RFA工程公司）；University of North Dakota（北达科他大学）
In this work we present a unified method of relative camera pose estimation from points and lines correspondences. Given a set of 2D points and lines correspondences in three views, of which two are known, a method has been developed for estimating the camera pose of the third view. Novelty of this algorithm is to combine both points and lines correspondences in the camera pose estimation which enables us to compute relative camera pose with a small number of feature correspondences. Our central idea is to exploit the tri-linear relationship between three views and generate a set of linear equ…
University of British Columbia（英属哥伦比亚大学）；Tongji University（同济大学）
Calibrating narrow field of view soccer cameras is challenging because there are very few field markings in the image. Unlike previous solutions, we propose a two-point method, which requires only two point correspondences given the prior knowledge of base location and orientation of a pan-tilt-zoom (PTZ) camera. We deploy this new calibration method to annotate pan-tilt-zoom data from soccer videos. The collected data are used as references for new images. We also propose a fast random forest method to predict pan-tilt angles without image-to-image feature matching, leading to an efficient ca…
Queen Mary University of London（伦敦玛丽女王大学）；Beihang University（北京航空航天大学）；Didi Chuxing（滴滴出行）
Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR). In this survey, we first introduce specific application areas and the evaluation metrics for camera localization pose according to different sub-tasks (learning-based 2D-2D task, feature-based 2D-3D task, and 3D-3D task). Then, we review common methods for structure-based camera pose estimation approaches, absolute pose regression and relative pose regression approaches by critically modelling the met…
University of British Columbia（不列颠哥伦比亚大学）；National University of Defense Technology（国防科学技术大学）
This work addresses camera selection, the task of predicting which camera should be "on air" from multiple candidate cameras for soccer broadcast. The task is challenging because of the scarcity of learning data with all candidate views. Meanwhile, broadcast videos are freely available on the Internet (e.g. Youtube). However, these videos only record the selected camera views, omitting the other candidate views. To overcome this problem, we first introduce a random survival forest (RSF) method to impute the incomplete data effectively. Then, we propose a spatial-appearance heatmap to describe …
Australian National University（澳大利亚国立大学）；Data61 – CSIRO（澳大利亚联邦科学与工业研究组织 Data61）
Estimating the 6-DoF pose of a camera from a single image relative to a pre-computed 3D point-set is an important task for many computer vision applications. Perspective-n-Point (PnP) solvers are routinely used for camera pose estimation, provided that a good quality set of 2D-3D feature correspondences are known beforehand. However, finding optimal correspondences between 2D key-points and a 3D point-set is non-trivial, especially when only geometric (position) information is known. Existing approaches to the simultaneous pose and correspondence problem use local optimisation, and are therefo…
