Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation
LIGM（LIGM实验室）；École des Ponts（巴黎路桥学院）；Univ Gustave Eiffel（Gustave Eiffel大学）；CNRS（法国国家科学研究中心）；IMS（IMS实验室）；University of Bordeaux（波尔多大学）；Bordeaux INP（波尔多国立综合理工学院）
Absolute camera pose estimation is usually addressed by sequentially solving two distinct subproblems: First a feature matching problem that seeks to establish putative 2D-3D correspondences, and then a Perspective-n-Point problem that minimizes, with respect to the camera pose, the sum of so-called Reprojection Errors (RE). We argue that generating putative 2D-3D correspondences 1) leads to an important loss of information that needs to be compensated as far as possible, within RE, through the choice of a robust loss and the tuning of its hyperparameters and 2) may lead to an RE that conveys erroneous data to the pose estimator. In this paper, we introduce the Neural Reprojection Error (NRE) as a substitute for RE. NRE allows to rethink the camera pose estimation problem by merging it with the feature learning problem, hence leveraging richer information than 2D-3D correspondences and eliminating the need for choosing a robust loss and its hyperparameters. Thus NRE can be used as training loss to learn image descriptors tailored for pose estimation. We also propose a coarse-to-fine optimization method able to very efficiently minimize a sum of NRE terms with respect to the camera pose. We experimentally demonstrate that NRE is a good substitute for RE as it significantly improves both the robustness and the accuracy of the camera pose estimate while being computationally and memory highly efficient. From a broader point of view, we believe this new way of merging deep learning and 3D geometry may be useful in other computer vision applications.
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）
We presented a separation based optimization algorithm which, rather than optimization the entire variables altogether, This would allow us to employ: 1) a class of nonlinear functions with three variables and 2) a convex quadratic multivariable polynomial, for minimization of reprojection error. Neglecting the inversion required to minimize the nonlinear functions, in this paper we demonstrate how separation allows eradication of matrix inversion.
Optical Image Stabilization (OIS) system in mobile devices reduces image blurring by steering lens to compensate for hand jitters. However, OIS changes intrinsic camera parameters (i.e. $\mathrm{K}$ matrix) dynamically which hinders accurate camera pose estimation or 3D reconstruction. Here we propose a novel neural network-based approach that estimates $\mathrm{K}$ matrix in real-time so that pose estimation or scene reconstruction can be run at camera native resolution for the highest accuracy on mobile devices. Our network design takes gratified projection model discrepancy feature and 3D p…
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…
Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration
School of Computer Science, Carnegie Mellon University（计算机科学系，卡内基梅隆大学）；Electrical and Computer Engineering, Carnegie Mellon University（电气与计算机工程，卡内基梅隆大学）；Harvard John A. Paulson School of Engineering And Applied Sciences, Harvard University（哈佛大学约翰·A·保罗森工程与应用科学学院）；Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；School of Mathematical Science, University of Nottingham（诺丁汉大学数学科学学院）；Weill Cornell Medicine, Cornell University（韦尔医学院，康奈尔大学）；Meta Reality Labs（Meta现实实验室）
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…
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…
Beihang University（北京航空航天大学）；National University of Singapore（新加坡国立大学）；Institute for Infocomm Research（信息通信研究院）
Existing methods detect the keypoints in a non-differentiable way, therefore they can not directly optimize the position of keypoints through back-propagation. To address this issue, we present a partially differentiable keypoint detection module, which outputs accurate sub-pixel keypoints. The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization. We also extract the descriptors in a sub-pixel way, and they are trained with the stable neural reprojection error loss. Moreover, a lightwe…
CNR–ISC (National Research Council - Institute for Complex Systems)（国家研究委员会-复杂系统研究所）；South China Agricultural University（华南农业大学）
The reconstruction of a scene via a stereo-camera system is a two-steps process, where at first images from different cameras are matched to identify the set of point-to-point correspondences that then will actually be reconstructed in the three dimensional real world. The performance of the system strongly relies of the calibration procedure, which has to be carefully designed to guarantee optimal results. We implemented three different calibration methods and we compared their performance over 19 datasets. We present the experimental evidence that, due to the image noise, a single set of par…
A Robust Error-Resistant View Selection Method for 3D Reconstruction
School of Artificial Intelligence and Computer Science, Jiangnan University（江南大学人工智能与计算机学院）；Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education（教育部智慧医疗技术工程研究中心）
Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras
École Centrale de Lyon, CNRS, INSA Lyon, Université Claude Bernard Lyon 1, Université Lumière Lyon 2, LIRIS, UMR5205, ENISE（Lyon中央理工学院、国家科学研究中心、里昂国立应用科学学院、克莱门特-伯纳德大学里昂1分校、里昂2大学、LIRIS、UMR5205、ENISE）
Czech Technical University in Prague（布拉格捷克理工大学）；ETH Zurich（苏黎世联邦理工学院）；Czech Academy of Sciences（捷克科学院）
We propose a novel method that tracks fast moving objects, mainly non-uniform spherical, in full 6 degrees of freedom, estimating simultaneously their 3D motion trajectory, 3D pose and object appearance changes with a time step that is a fraction of the video frame exposure time. The sub-frame object localization and appearance estimation allows realistic temporal super-resolution and precise shape estimation. The method, called TbD-3D (Tracking by Deblatting in 3D) relies on a novel reconstruction algorithm which solves a piece-wise deblurring and matting problem. The 3D rotation is estimated…
Active depth cameras suffer from several limitations, which cause incomplete and noisy depth maps, and may consequently affect the performance of RGB-D Odometry. To address this issue, this paper presents a visual odometry method based on point and line features that leverages both measurements from a depth sensor and depth estimates from camera motion. Depth estimates are generated continuously by a probabilistic depth estimation framework for both types of features to compensate for the lack of depth measurements and inaccurate feature depth associations. The framework models explicitly the …
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Toyota Research Institute（丰田研究院）
Camera calibration is integral to robotics and computer vision algorithms that seek to infer geometric properties of the scene from visual input streams. In practice, calibration is a laborious procedure requiring specialized data collection and careful tuning. This process must be repeated whenever the parameters of the camera change, which can be a frequent occurrence for mobile robots and autonomous vehicles. In contrast, self-supervised depth and ego-motion estimation approaches can bypass explicit calibration by inferring per-frame projection models that optimize a view synthesis objectiv…
Neural Radiance Fields (NeRFs) aim to synthesize novel views of objects and scenes, given the object-centric camera views with large overlaps. However, we conjugate that this paradigm does not fit the nature of the street views that are collected by many self-driving cars from the large-scale unbounded scenes. Also, the onboard cameras perceive scenes without much overlapping. Thus, existing NeRFs often produce blurs, 'floaters' and other artifacts on street-view synthesis. In this paper, we propose a new street-view NeRF (S-NeRF) that considers novel view synthesis of both the large-scale bac…
Implementation of a Zed 2i Stereo Camera for High-Frequency Shoreline Change and Coastal Elevation Monitoring
College of Engineering and Computer Science, Texas A&M University–Corpus Christi（德克萨斯农工大学科珀斯克里斯蒂分校工程与计算机科学学院）；Conrad Blucher Institute for Surveying and Science（康拉德·布鲁克测绘与科学研究院）
This work is concerned with camera pose estimation from correspondences of 3D/2D lines, i. e. with the Perspective-n-Line (PnL) problem. We focus on large line sets, which can be efficiently solved by methods using linear formulation of PnL. We propose a novel method "DLT-Combined-Lines" based on the Direct Linear Transformation (DLT) algorithm, which benefits from a new combination of two existing DLT methods for pose estimation. The method represents 2D structure by lines, and 3D structure by both points and lines. The redundant 3D information reduces the minimum required line correspondence…
While depth cameras and inertial sensors have been frequently leveraged for human action recognition, these sensing modalities are impractical in many scenarios where cost or environmental constraints prohibit their use. As such, there has been recent interest on human action recognition using low-cost, readily-available RGB cameras via deep convolutional neural networks. However, many of the deep convolutional neural networks proposed for action recognition thus far have relied heavily on learning global appearance cues directly from imaging data, resulting in highly complex network architect…
Weizmann Institute of Science（魏茨曼科学研究学院）；NVIDIA Research（英伟达研究院）
Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses and 3D scene structure in multiview settings with deep networks is still outstanding. Inspired by projective factorization for Structure from Motion (SFM) and by deep matrix completion techniques, we propose a neural network architecture that, given a set of point tracks in multiple images of a static scene, recovers both the camera parameters and a (sparse…
École normale supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；INRIA（法国国家信息与自动化研究所）；LIGM（加斯帕尔·蒙日信息实验室）；École des Ponts（巴黎高科路桥学院）；Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；Czech Institute of Informatics, Robotics and Cybernetics（捷克信息学、机器人与控制论研究所）；Czech Technical University in Prague（布拉格捷克理工大学）
We introduce an approach for recovering the 6D pose of multiple known objects in a scene captured by a set of input images with unknown camera viewpoints. First, we present a single-view single-object 6D pose estimation method, which we use to generate 6D object pose hypotheses. Second, we develop a robust method for matching individual 6D object pose hypotheses across different input images in order to jointly estimate camera viewpoints and 6D poses of all objects in a single consistent scene. Our approach explicitly handles object symmetries, does not require depth measurements, is robust to…
Seoul National University of Science and Technology（首尔科学技术大学）
In this paper, we propose a dense depth estimation pipeline for multiview 360° images. The proposed pipeline leverages a spherical camera model that compensates for radial distortion in 360° images. The key contribution of this paper is the extension of a spherical camera model to multiview by introducing a translation scaling scheme. Moreover, we propose an effective dense depth estimation method by setting virtual depth and minimizing photonic reprojection error. We validate the performance of the proposed pipeline using the images of natural scenes as well as the synthesized dataset for qua…
Leibniz Universität Hannover（汉诺威莱布尼茨大学）；Hannover, Germany（德国汉诺威（注：此处原文本中该部分为地址信息，根据提取规则，不应作为机构提取，正确机构仅为Leibniz Universität Hannover））
This paper addresses the problem of 3D human pose estimation from single images. While for a long time human skeletons were parameterized and fitted to the observation by satisfying a reprojection error, nowadays researchers directly use neural networks to infer the 3D pose from the observations. However, most of these approaches ignore the fact that a reprojection constraint has to be satisfied and are sensitive to overfitting. We tackle the overfitting problem by ignoring 2D to 3D correspondences. This efficiently avoids a simple memorization of the training data and allows for a weakly supe…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Intel Labs（英特尔实验室）
We address the problem of learning accurate 3D shape and camera pose from a collection of unlabeled category-specific images. We train a convolutional network to predict both the shape and the pose from a single image by minimizing the reprojection error: given several views of an object, the projections of the predicted shapes to the predicted camera poses should match the provided views. To deal with pose ambiguity, we introduce an ensemble of pose predictors which we then distill to a single "student" model. To allow for efficient learning of high-fidelity shapes, we represent the shapes by…
In this paper, we present a new system for live collaborative dense surface reconstruction. Cooperative robotics, multi participant augmented reality and human-robot interaction are all examples of situations where collaborative mapping can be leveraged for greater agent autonomy. Our system builds on ElasticFusion to allow a number of cameras starting with unknown initial relative positions to maintain local maps utilising the original algorithm. Carrying out visual place recognition across these local maps the system can identify when two maps overlap in space, providing an inter-map constra…
Through capturing spatial and angular radiance distribution, light field cameras introduce new capabilities that are not possible with conventional cameras. So far in the light field imaging literature, the focus has been on the theory and applications of single light field capture. By combining multiple light fields, it is possible to obtain new capabilities and enhancements, and even exceed physical limitations, such as spatial resolution and aperture size of the imaging device. In this paper, we present an algorithm to register and stitch multiple light fields. We utilize the regularity of …
We propose a deep neural network architecture to infer dense depth from an image and a sparse point cloud. It is trained using a video stream and corresponding synchronized sparse point cloud, as obtained from a LIDAR or other range sensor, along with the intrinsic calibration parameters of the camera. At inference time, the calibration of the camera, which can be different than the one used for training, is fed as an input to the network along with the sparse point cloud and a single image. A Calibrated Backprojection Layer backprojects each pixel in the image to three-dimensional space using…
Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the motion of dynamic objects. In this paper, we propose a novel Dyna-Depthformer framework, which predicts scene depth and 3D motion field jointly and aggregates multi-frame information with transformer. Our contributions are two-fold. First, we leverage multi-view correlation through a series of self- and cross-attention layers in order to obtain enhanced depth …
This paper revisits the problem of continuous-time structure from motion, and introduces a number of extensions that improve convergence and efficiency. The formulation with a $\mathcal{C}^2$-continuous spline for the trajectory naturally incorporates inertial measurements, as derivatives of the sought trajectory. We analyse the behaviour of split interpolation on $\mathbb{SO}(3)$ and on $\mathbb{R}^3$, and a joint interpolation on $\mathbb{SE}(3)$, and show that the latter implicitly couples the direction of translation and rotation. Such an assumption can make good sense for a camera mounted…
Ifremer（法国海洋开发研究院）；Université de Toulon（土伦大学）；Aix Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）
Some recent visual-based relocalization algorithms rely on deep learning methods to perform camera pose regression from image data. This paper focuses on the loss functions that embed the error between two poses to perform deep learning based camera pose regression. Existing loss functions are either difficult-to-tune multi-objective functions or present unstable reprojection errors that rely on ground truth 3D scene points and require a two-step training. To deal with these issues, we introduce a novel loss function which is based on a multiplane homography integration. This new function does…
Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods. Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with…
Massachusetts Institute of Technology（麻省理工学院）；Stevens Institute of Technology（史蒂文斯理工学院）
We propose a methodology for robust, real-time place recognition using an imaging lidar, which yields image-quality high-resolution 3D point clouds. Utilizing the intensity readings of an imaging lidar, we project the point cloud and obtain an intensity image. ORB feature descriptors are extracted from the image and encoded into a bag-of-words vector. The vector, used to identify the point cloud, is inserted into a database that is maintained by DBoW for fast place recognition queries. The returned candidate is further validated by matching visual feature descriptors. To reject matching outlie…
Deep learning has shown to be effective for robust and real-time monocular image relocalisation. In particular, PoseNet is a deep convolutional neural network which learns to regress the 6-DOF camera pose from a single image. It learns to localize using high level features and is robust to difficult lighting, motion blur and unknown camera intrinsics, where point based SIFT registration fails. However, it was trained using a naive loss function, with hyper-parameters which require expensive tuning. In this paper, we give the problem a more fundamental theoretical treatment. We explore a number…
Fraunhofer IOSB（弗劳恩霍夫IOSB研究所）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
The comparison of current image data with existing 3D model data of a scene provides an efficient method to keep models up to date. In order to transfer information between 2D and 3D data, a preliminary co-registration is necessary. In this paper, we present a concept to automatically co-register aerial imagery and untextured 3D model data. To refine a given initial camera pose, our algorithm computes dense correspondence fields using SIFT flow between gradient representations of the model and camera image, from which 2D-3D correspondences are obtained. These correspondences are then used in a…
ClearLines - Camera Calibration from Straight Lines
Johannes Kepler University Linz（约翰·开普勒大学林茨）；Department Intelligent Transport Systems（智能交通运输系统部门）；Intelligent Systems Functions Department（智能系统功能部门）；IAV GmbH（IAV公司）
A near-optimal reconstruction of the radiance of a High Dynamic Range scene from an exposure stack can be obtained by modeling the camera noise distribution. The latent radiance is then estimated using Maximum Likelihood Estimation. But this requires a well-calibrated noise model of the camera, which is difficult to obtain in practice. We show that an unbiased estimation of comparable variance can be obtained with a simpler Poisson noise estimator, which does not require the knowledge of camera-specific noise parameters. We demonstrate this empirically for four different cameras, ranging from …
Instituto de Investigación en Ingeniería de Aragón (I3A)（阿拉贡工程研究院（I3A））；Universidad de Zaragoza（萨拉戈萨大学）
Monocular SLAM in deformable scenes will open the way to multiple medical applications like computer-assisted navigation in endoscopy, automatic drug delivery or autonomous robotic surgery. In this paper we propose a novel method to simultaneously track the camera pose and the 3D scene deformation, without any assumption about environment topology or shape. The method uses an illumination-invariant photometric method to track image features and estimates camera motion and deformation combining reprojection error with spatial and temporal regularization of deformations. Our results in simulated…
