In 3D reconstruction, the recovery of the calibration parameters of the cameras is paramount since it provides metric information about the observed scene, e.g., measures of angles and ratios of distances. Autocalibration enables the estimation of the camera parameters without using a calibration device, but by enforcing simple constraints on the camera parameters. In the absence of information about the internal camera parameters such as the focal length and the principal point, the knowledge of the camera pixel shape is usually the only available constraint. Given a projective reconstruction of a rigid scene, we address the problem of the autocalibration of a minimal set of cameras with known pixel shape and otherwise arbitrarily varying intrinsic and extrinsic parameters. We propose an algorithm that only requires 5 cameras (the theoretical minimum), thus halving the number of cameras required by previous algorithms based on the same constraint. To this purpose, we introduce as our basic geometric tool the six-line conic variety (SLCV), consisting in the set of planes intersecting six given lines of 3D space in points of a conic. We show that the set of solutions of the Euclidean upgrading problem for three cameras with known pixel shape can be parameterized in a computationally efficient way. This parameterization is then used to solve autocalibration from five or more cameras, reducing the three-dimensional search space to a two-dimensional one. We provide experiments with real images showing the good performance of the technique.
Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel approach based on neural networks for depth estimation that combines stereo from dual cameras with stereo from a dual-pixel sensor, which is increasingly common on consumer cameras. Our network uses a novel architecture to fuse these two sources of information and can overcome the above-mentioned limitations of pure binocular stereo matching. Our method provides a dense depth map with sharp edges, which is crucial fo…
ETH Zurich（苏黎世联邦理工学院）；Chalmers University of Technology（查尔姆斯理工大学）；Eigenvision；Ecole des Ponts（巴黎高科路桥学校）；Microsoft（微软）；Czech Technical University in Prague（捷克理工大学）
Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints or ties the model parameters to a specific scene. In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms. We introduce PixLoc, a scene-agnostic neural network that estimates an accurate 6-DoF pose from…
1 Research School of Engineering, The \ National University (ANU), Australia；2 Australia Centre of Excellence for \ Vision (ACRV), Australia
Large field-of-view fisheye lens cameras have attracted more and more researchers' attention in the field of robotics. However, there does not exist a convenient off-the-shelf stereo rectification approach which can be applied directly to fisheye stereo rig. One obvious drawback of existing methods is that the resampling distortion (which is defined as the loss of pixels due to under-sampling and the creation of new pixels due to over-sampling during rectification process) is severe if we want to obtain a rectification with epipolar line (not epipolar circle) constraint. To overcome this weakn…
Deep learning techniques have enabled rapid progress in monocular depth estimation, but their quality is limited by the ill-posed nature of the problem and the scarcity of high quality datasets. We estimate depth from a single camera by leveraging the dual-pixel auto-focus hardware that is increasingly common on modern camera sensors. Classic stereo algorithms and prior learning-based depth estimation techniques under-perform when applied on this dual-pixel data, the former due to too-strong assumptions about RGB image matching, and the latter due to not leveraging the understanding of optics …
Perceiving 3D information is of paramount importance in many applications of computer vision. Recent advances in monocular depth estimation have shown that gaining such knowledge from a single camera input is possible by training deep neural networks to predict inverse depth and pose, without the necessity of ground truth data. The majority of such approaches, however, require camera parameters to be fed explicitly during training. As a result, image sequences from wild cannot be used during training. While there exist methods which also predict camera intrinsics, their performance is not on p…
Australian National University（澳大利亚国立大学）；CSIRO（澳大利亚联邦科学与工业研究组织）
Stereo camera systems play an important role in robotics applications to perceive the 3D world. However, conventional cameras have drawbacks such as low dynamic range, motion blur and latency due to the underlying frame-based mechanism. Event cameras address these limitations as they report the brightness changes of each pixel independently with a fine temporal resolution, but they are unable to acquire absolute intensity information directly. Although integrated hybrid event-frame sensors (eg., DAVIS) are available, the quality of data is compromised by coupling at the pixel level in the circ…
We propose Stereo Direct Sparse Odometry (Stereo DSO) as a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras. It jointly optimizes for all the model parameters within the active window, including the intrinsic/extrinsic camera parameters of all keyframes and the depth values of all selected pixels. In particular, we propose a novel approach to integrate constraints from static stereo into the bundle adjustment pipeline of temporal multi-view stereo. Real-time optimization is realized by sampling pixels uniformly from image reg…
Beijing Institute of Aerospace Systems Engineering（北京宇航系统工程研究所）；China Academy of Launch Vehicle Technology（中国运载火箭技术研究院）
Event cameras are a new type of sensors that are different from traditional cameras. Each pixel is triggered asynchronously by event. The trigger event is the change of the brightness irradiated on the pixel. If the increment or decrement of brightness is higher than a certain threshold, an event is output. Compared with traditional cameras, event cameras have the advantages of high dynamic range and no motion blur. Since events are caused by the apparent motion of intensity edges, the majority of 3D reconstructed maps consist only of scene edges, i.e., semi-dense maps, which is not enough for…
Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features and propagate large errors to the final geometry. In this paper, we refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views: we first adjust the initial keypoint locations prior to any geometric estimation, and subsequently refine points and camera poses as a post-processing. This refinement is robu…
In this paper we present ADOP, a novel point-based, differentiable neural rendering pipeline. Like other neural renderers, our system takes as input calibrated camera images and a proxy geometry of the scene, in our case a point cloud. To generate a novel view, the point cloud is rasterized with learned feature vectors as colors and a deep neural network fills the remaining holes and shades each output pixel. The rasterizer renders points as one-pixel splats, which makes it very fast and allows us to compute gradients with respect to all relevant input parameters efficiently. Furthermore, our …
NVIDIA（英伟达）；Georgia Institute of Technology（佐治亚理工学院）
We present a parallelized optimization method based on fast Neural Radiance Fields (NeRF) for estimating 6-DoF pose of a camera with respect to an object or scene. Given a single observed RGB image of the target, we can predict the translation and rotation of the camera by minimizing the residual between pixels rendered from a fast NeRF model and pixels in the observed image. We integrate a momentum-based camera extrinsic optimization procedure into Instant Neural Graphics Primitives, a recent exceptionally fast NeRF implementation. By introducing parallel Monte Carlo sampling into the pose es…
Michigan State University（密歇根州立大学）；Ford Motor Company（福特汽车公司）
While radar and video data can be readily fused at the detection level, fusing them at the pixel level is potentially more beneficial. This is also more challenging in part due to the sparsity of radar, but also because automotive radar beams are much wider than a typical pixel combined with a large baseline between camera and radar, which results in poor association between radar pixels and color pixel. A consequence is that depth completion methods designed for LiDAR and video fare poorly for radar and video. Here we propose a radar-to-pixel association stage which learns a mapping from rada…
A scanning pixel camera is a novel low-cost, low-power sensor that is not diffraction limited. It produces data as a sequence of samples extracted from various parts of the scene during the course of a scan. It can provide very detailed images at the expense of samplerates and slow image acquisition time. This paper proposes a new algorithm which allows the sensor to adapt the samplerate over the course of this sequence. This makes it possible to overcome some of these limitations by minimising the bandwidth and time required to image and transmit a scene, while maintaining image quality. We e…
Computing the epipolar geometry from feature points between cameras with very different viewpoints is often error prone, as an object's appearance can vary greatly between images. For such cases, it has been shown that using motion extracted from video can achieve much better results than using a static image. This paper extends these earlier works based on the scene dynamics. In this paper we propose a new method to compute the epipolar geometry from a video stream, by exploiting the following observation: For a pixel p in Image A, all pixels corresponding to p in Image B are on the same epip…
UCLouvain（鲁汶大学）；Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico（高等技术学院）；Universidade de Lisboa（里斯本大学）
This paper introduces a single-pixel HyperSpectral (HS) imaging framework based on Fourier Transform Interferometry (FTI). By combining a space-time coding of the light illumination with partial interferometric observations of a collimated light beam (observed by a single pixel), our system benefits from (i) reduced measurement rate and light-exposure of the observed object compared to common (Nyquist) FTI imagers, and (ii) high spectral resolution as desirable in, e.g., Fluorescence Spectroscopy (FS). From the principles of compressive sensing with multilevel sampling, our method leverages th…
We quantify the generalization of a convolutional neural network (CNN) trained to identify cars. First, we perform a series of experiments to train the network using one image dataset - either synthetic or from a camera - and then test on a different image dataset. We show that generalization between images obtained with different cameras is roughly the same as generalization between images from a camera and ray-traced multispectral synthetic images. Second, we use ISETAuto, a soft prototyping tool that creates ray-traced multispectral simulations of camera images, to simulate sensor images wi…
Tampere University of Technology（坦佩雷理工大学）；Intel Finland（英特尔芬兰公司）；Czech Technical University in Prague（布拉格捷克理工大学）
We present a statistical color constancy method that relies on novel gray pixel detection and mean shift clustering. The method, called Mean Shifted Grey Pixel -- MSGP, is based on the observation: true-gray pixels are aligned towards one single direction. Our solution is compact, easy to compute and requires no training. Experiments on two real-world benchmarks show that the proposed approach outperforms state-of-the-art methods in the camera-agnostic scenario. In the setting where the camera is known, MSGP outperforms all statistical methods.
Osaka University（大阪大学）；Graduate School of Engineering Science（工学研究科）
We propose a novel projector-camera system (ProCams) in which each pixel has both projection and capturing capabilities. Our proposed ProCams solves the difficulty of obtaining precise pixel correspondence between the projector and the camera. We implemented a proof-of-concept ProCams prototype and demonstrated its applicability to a dynamic projection mapping.
Université de technologie de Compiègne (UTC), CNRS, Heudiasyc（贡比涅技术大学（UTC），法国国家科学研究中心（CNRS），Heudiasyc实验室）
Event cameras capture changes of illumination in the observed scene rather than accumulating light to create images. Thus, they allow for applications under high-speed motion and complex lighting conditions, where traditional framebased sensors show their limits with blur and over- or underexposed pixels. Thanks to these unique properties, they represent nowadays an highly attractive sensor for ITS-related applications. Event-based optical flow (EBOF) has been studied following the rise in popularity of these neuromorphic cameras. The recent arrival of high-definition neuromorphic sensors, how…
Event cameras output asynchronous events to represent intensity changes with a high temporal resolution, even under extreme lighting conditions. Currently, most of the existing works use a single contrast threshold to estimate the intensity change of all pixels. However, complex circuit bias and manufacturing imperfections cause biased pixels and mismatch contrast threshold among pixels, which may lead to undesirable outputs. In this paper, we propose a new event camera model and two calibration approaches which cover event-only cameras and hybrid image-event cameras. When intensity images are…
Structured light illumination is an active 3-D scanning technique based on projecting/capturing a set of striped patterns and measuring the warping of the patterns as they reflect off a target object's surface. As designed, each pixel in the camera sees exactly one pixel from the projector; however, there are exceptions to this when the scanned surface has a complicated geometry with step edges and other discontinuities in depth or where the target surface has specularities that reflect light away from the camera. These situations are generally referred to multipath where a given camera pixel …
Many mobile manufacturers recently have adopted Dual-Pixel (DP) sensors in their flagship models for faster auto-focus and aesthetic image captures. Despite their advantages, research on their usage for 3D facial understanding has been limited due to the lack of datasets and algorithmic designs that exploit parallax in DP images. This is because the baseline of sub-aperture images is extremely narrow and parallax exists in the defocus blur region. In this paper, we introduce a DP-oriented Depth/Normal network that reconstructs the 3D facial geometry. For this purpose, we collect a DP facial da…
The measurement rate of cameras that take spatially multiplexed measurements by using spatial light modulators (SLM) is often limited by the switching speed of the SLMs. This is especially true for single-pixel cameras where the photodetector operates at a rate that is many orders-of-magnitude greater than the SLM. We study the factors that determine the measurement rate for such spatial multiplexing cameras (SMC) and show that increasing the number of pixels in the device improves the measurement rate, but there is an optimum number of pixels (typically, few thousands) beyond which the measur…
Beijing Institute of Aerospace Systems Engineering（北京宇航系统工程研究所）；Space Engineering University（航天工程大学）；China Academy of Launch Vehicle Technology（中国运载火箭技术研究院）
Event camera is a new type of sensor that is different from traditional cameras. Each pixel is triggered asynchronously by an event. The trigger event is the change of the brightness irradiated on the pixel. If the increment or decrement is higher than a certain threshold, the event is output. Compared with traditional cameras, event cameras have the advantages of high temporal resolution, low latency, high dynamic range, low bandwidth and low power consumption. We carried out a series of observation experiments in a simulated space lighting environment. The experimental results show that the …
Graz University of Technology（格拉茨技术大学）；Austrian Institute Of Technology（奥地利技术研究院）
Event cameras or neuromorphic cameras mimic the human perception system as they measure the per-pixel intensity change rather than the actual intensity level. In contrast to traditional cameras, such cameras capture new information about the scene at MHz frequency in the form of sparse events. The high temporal resolution comes at the cost of losing the familiar per-pixel intensity information. In this work we propose a variational model that accurately models the behaviour of event cameras, enabling reconstruction of intensity images with arbitrary frame rate in real-time. Our method is formu…
Security concerns has been kept on increasing, so it is important for everyone to keep their property safe from thefts and destruction. So the need for surveillance techniques are also increasing. The system has been developed to detect the motion in a video. A system has been developed for real time applications by using the techniques of background subtraction and frame differencing. In this system, motion is detected from the webcam or from the real time video. Background subtraction and frames differencing method has been used to detect the moving target. In background subtraction method, …
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Event cameras are biologically-inspired sensors that gather the temporal evolution of the scene. They capture pixel-wise brightness variations and output a corresponding stream of asynchronous events. Despite having multiple advantages with respect to traditional cameras, their use is partially prevented by the limited applicability of traditional data processing and vision algorithms. To this aim, we present a framework which exploits the output stream of event cameras to synthesize RGB frames, relying on an initial or a periodic set of color key-frames and the sequence of intermediate events…
University of Turku（图尔库大学）；Politecnico di Milano（米兰理工大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）
Event cameras, i.e., the Dynamic and Active-pixel Vision Sensor (DAVIS) ones, capture the intensity changes in the scene and generates a stream of events in an asynchronous fashion. The output rate of such cameras can reach up to 10 million events per second in high dynamic environments. DAVIS cameras use novel vision sensors that mimic human eyes. Their attractive attributes, such as high output rate, High Dynamic Range (HDR), and high pixel bandwidth, make them an ideal solution for applications that require high-frequency tracking. Moreover, applications that operate in challenging lighting…
University of Maryland Institute for Advanced Computer Studies（马里兰大学高级计算机研究所）；ETH Zurich（苏黎世联邦理工学院）
We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO - which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates pixel-wise independently moving object segmentation and computes per-object 3D translational velocities for moving objects. We also train a shallow network …
University of Southern California（南加利福尼亚大学）；Information Sciences Institute（信息科学研究所）
Hyperspectral cameras generate a large amount of data due to the presence of hundreds of spectral bands as opposed to only three channels (red, green, and blue) in traditional cameras. This requires a significant amount of data transmission between the hyperspectral image sensor and a processor used to classify/detect/track the images, frame by frame, expending high energy and causing bandwidth and security bottlenecks. To mitigate this problem, we propose a form of processing-in-pixel (PIP) that leverages advanced CMOS technologies to enable the pixel array to perform a wide range of complex …
CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation（多模态人工智能系统国家重点实验室（MAIS）自动化研究所）；School of Artificial Intelligence（人工智能学院）
Technical University of Denmark（丹麦技术大学）；University of Southern Denmark（南丹麦大学）
The most prevalent routine for camera calibration is based on the detection of well-defined feature points on a purpose-made calibration artifact. These could be checkerboard saddle points, circles, rings or triangles, often printed on a planar structure. The feature points are first detected and then used in a nonlinear optimization to estimate the internal camera parameters.We propose a new method for camera calibration using the principle of inverse rendering. Instead of relying solely on detected feature points, we use an estimate of the internal parameters and the pose of the calibration …
Xidian University（西安电子科技大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Xidian Guangzhou Institute of Technology（西安电子科技大学广州研究院）
This paper addresses the challenging unsupervised scene flow estimation problem by jointly learning four low-level vision sub-tasks: optical flow $\textbf{F}$, stereo-depth $\textbf{D}$, camera pose $\textbf{P}$ and motion segmentation $\textbf{S}$. Our key insight is that the rigidity of the scene shares the same inherent geometrical structure with object movements and scene depth. Hence, rigidity from $\textbf{S}$ can be inferred by jointly coupling $\textbf{F}$, $\textbf{D}$ and $\textbf{P}$ to achieve more robust estimation. To this end, we propose a novel scene flow framework named EffiSc…
Accurately calibrating light field camera is essential to its applications. Rapid progress has been made in this area in the past decades. In this paper, detailed analysis was first performed towards the state of the art projection models for calibration which were further interpreted in three representations, including the correspondence between rays and pixels, 3D physical points and pixels and between 3D physical points and 3D signal structure of the captured light field. Based on the analysis, parameters in the projection model were grouped into direction parameter set and depth parameter …
We have designed a single-pixel camera with imaging around corners based on computational ghost imaging. It can obtain the image of an object when the camera cannot look at the object directly. Our imaging system explores the fact that a bucket detector in a ghost imaging setup has no spatial resolution capability. A series of experiments have been designed to confirm our predictions. This camera has potential applications for imaging around corner or other similar environments where the object cannot be observed directly.
Institute of Neuroinformatics, University of Z\"urich；ETH Z\"urich, Z\"urich, Switzerland
Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little brightness variation. We propose using a visual transformer (ViT) architecture to leverage its ability to process a variable-length input. The input to the ViT consists of events that are accumulated into time bins and spatially separated into non-overlapping sub-regions called patches. Patches are selected when the number of nonzero pixel locations within a sub-region is above a threshold. We show that by fine-tuning a ViT model on the se…
University of South Bohemia in České Budějovice（南波希米亚大学）
In this paper, we introduce a novel - physico-chemical - approach for calibration of a digital camera chip. This approach utilizes results of measurement of incident light spectra of calibration films of different levels of gray for construction of calibration curve (number of incident photons vs. image pixel intensity) for each camera pixel. We show spectral characteristics of such corrected digital raw image files (a primary camera signal) and demonstrate their suitability for next image processing and analysis.
University College London（伦敦大学学院）；Mullard Space Science Laboratory（穆拉德空间科学实验室）
This paper investigates how the inherent quantization of camera sensors introduces uncertainty in the calculated position of an observed feature during 3-D mapping. It is typically assumed that pixels and scene features are points, however, a pixel is a two-dimensional area that maps onto multiple points in the scene. This uncertainty region is a bound for quantization error in the calculated point positions. Earlier studies calculated the volume of two intersecting pixel views, approximated as a cuboid, by projecting pyramids and cones from the pixels into the scene. In this paper, we reverse…
