Inferring the pose and shape of vehicles in 3D from a movable platform still remains a challenging task due to the projective sensing principle of cameras, difficult surface properties e.g. reflections or transparency, and illumination changes between images. In this paper, we propose to use 3D shape and motion priors to regularize the estimation of the trajectory and the shape of vehicles in sequences of stereo images. We represent shapes by 3D signed distance functions and embed them in a low-dimensional manifold. Our optimization method allows for imposing a common shape across all image observations along an object track. We employ a motion model to regularize the trajectory to plausible object motions. We evaluate our method on the KITTI dataset and show state-of-the-art results in terms of shape reconstruction and pose estimation accuracy.
Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover（莱布尼茨汉诺威大学摄影测量与地理信息研究所）
The 3D reconstruction of objects is a prerequisite for many highly relevant applications of computer vision such as mobile robotics or autonomous driving. To deal with the inverse problem of reconstructing 3D objects from their 2D projections, a common strategy is to incorporate prior object knowledge into the reconstruction approach by establishing a 3D model and aligning it to the 2D image plane. However, current approaches are limited due to inadequate shape priors and the insufficiency of the derived image observations for a reliable alignment with the 3D model. The goal of this paper is t…
The retrieval of the 3D pose and shape of objects from images is an ill-posed problem. A common way to object reconstruction is to match entities such as keypoints, edges, or contours of a deformable 3D model, used as shape prior, to their corresponding entities inferred from the image. However, such approaches are highly sensitive to model initialisation, imprecise keypoint localisations and/or illumination conditions. In this paper, we present a probabilistic approach for shape-aware 3D vehicle reconstruction from stereo images that leverages the outputs of a novel multi-task CNN. Specifical…
We introduce VERTEX, an effective solution to recover 3D shape and intrinsic texture of vehicles from uncalibrated monocular input in real-world street environments. To fully utilize the template prior of vehicles, we propose a novel geometry and texture joint representation, based on implicit semantic template mapping. Compared to existing representations which infer 3D texture distribution, our method explicitly constrains the texture distribution on the 2D surface of the template as well as avoids limitations of fixed resolution and topology. Moreover, by fusing the global and local feature…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；FZI Research Center for Information Technology（FZI信息技术研究中心）
The Large-scale 3D reconstruction, texturing and semantic mapping are nowadays widely used for automated driving vehicles, virtual reality and automatic data generation. However, most approaches are developed for RGB-D cameras with colored dense point clouds and not suitable for large-scale outdoor environments using sparse LiDAR point clouds. Since a 3D surface can be usually observed from multiple camera images with different view poses, an optimal image patch selection for the texturing and an optimal semantic class estimation for the semantic mapping are still challenging. To address these…
Uber ATG；University of Toronto（多伦多大学）；Massachusetts Institute of Technology（麻省理工学院）
Reconstructing high-quality 3D objects from sparse, partial observations from a single view is of crucial importance for various applications in computer vision, robotics, and graphics. While recent neural implicit modeling methods show promising results on synthetic or dense data, they perform poorly on sparse and noisy real-world data. We discover that the limitations of a popular neural implicit model are due to lack of robust shape priors and lack of proper regularization. In this work, we demonstrate highquality in-the-wild shape reconstruction using: (i) a deep encoder as a robust-initia…
The Hong Kong University of Science and Technology（香港科技大学）；Kwai Inc.（快手公司）
We present a novel end-to-end framework named as GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view. GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass. Extensive experiments show that our diverse feature extraction and fusion scheme can greatly improve model performance. Based on a divide-and-conquer 3D shape representation strategy, GSNet reconstructs 3D vehicle shape with great detail (1352 vertices and 2700…
In the current computer vision era classifying scenes through video surveillance systems is a crucial task. Artificial Intelligence (AI) Video Surveillance technologies have been advanced remarkably while artificial intelligence and deep learning ascended into the system. Adopting the superior compounds of deep learning visual classification methods achieved enormous accuracy in classifying visual scenes. However, the visual classifiers face difficulties examining the scenes in dark visible areas, especially during the nighttime. Also, the classifiers face difficulties in identifying the conte…
This paper explores the current state-of-the-art of object reconstruction from multiple orthographic drawings using deep neural networks. It proposes two algorithms to extract multiple views from a single image. The paper proposes a system based on pixel-aligned implicit functions (PIFu) and develops an advanced sampling strategy to generate signed distance samples. It also compares this approach to depth map regression from multiple views. Additionally, the paper uses a novel dataset for vehicle reconstruction from the racing game Assetto Corsa, which features higher quality models than the c…
An approach is proposed for high resolution 3D reconstruction of an object using a Micro Air Vehicle (MAV). A system is described which autonomously captures images and performs a dense 3D reconstruction via structure from motion with no prior knowledge of the environment. Only the MAVs own sensors, the front facing camera and the Inertial Measurement Unit (IMU) are utilized. Precision agriculture is considered as an example application for the system.
Robotics Research Center, KCIS, IIIT Hyderabad（印度海得拉巴国际信息技术研究所 KCIS 机器人研究中心）；Montreal Institute of Learning Algorithms (MILA), Universite de Montreal（蒙特利尔大学蒙特利尔学习算法研究所）
Accurate localization of other traffic participants is a vital task in autonomous driving systems. State-of-the-art systems employ a combination of sensing modalities such as RGB cameras and LiDARs for localizing traffic participants, but most such demonstrations have been confined to plain roads. We demonstrate, to the best of our knowledge, the first results for monocular object localization and shape estimation on surfaces that do not share the same plane with the moving monocular camera. We approximate road surfaces by local planar patches and use semantic cues from vehicles in the scene t…
Vehicle-centric Perception via Multimodal Structured Pre-training
Information Materials and Intelligent Sensing Laboratory of Anhui Province（安徽省信息材料与智能感知实验室）；Anhui Provincial Key Laboratory of Multimodal Cognitive Computation（安徽省多模态认知计算重点实验室）；the School of Artificial Intelligence, Anhui University（安徽大学人工智能学院）；School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
A key question in the problem of 3D reconstruction is how to train a machine or a robot to model 3D objects. Many tasks like navigation in real-time systems such as autonomous vehicles directly depend on this problem. These systems usually have limited computational power. Despite considerable progress in 3D reconstruction systems in recent years, applying them to real-time systems such as navigation systems in autonomous vehicles is still challenging due to the high complexity and computational demand of the existing methods. This study addresses current problems in reconstructing objects dis…
CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting
Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）；Beijing Institute of Technology（北京理工大学）；Nanyang Technological University（南洋理工大学）；Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；Beijing University of Technology（北京理工大学）；Baidu Inc（百度公司）；Peking University（北京大学）；Shanghai AI Lab（上海人工智能实验室）；Westlake University（西湖大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
提出 CRUISE 框架，利用分解式 Gaussian Splatting 重建并编辑 V2X 场景，实现多视角数据增强，提升协同 3D 检测、跟踪及边角案例生成能力。
Institute for Infocomm Research (IR), A*STAR（新加坡科技研究局资讯通信研究院）；Nanyang Technological University (NTU)（南洋理工大学）；University of Illinois at Urbana-Champaign (UIUC)（伊利诺伊大学厄巴纳-香槟分校）；Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）
Advances in Unmanned Aerial Vehicle (UAV) opens venues for application such as tunnel inspection. Owing to its versatility to fly inside the tunnels, it can quickly identify defects and potential problems related to safety. However, long tunnels, especially with repetitive or uniform structures pose a significant problem for UAV navigation. Furthermore, post-processing visual data from the camera mounted on the UAV is required to generate useful information for the inspection task. In this work, we design a UAV with a single rotating camera to accomplish the task. Compared to other platforms, …
Self-driving vehicle vision systems must deal with an extremely broad and challenging set of scenes. They can potentially exploit an enormous amount of training data collected from vehicles in the field, but the volumes are too large to train offline naively. Not all training instances are equally valuable though, and importance sampling can be used to prioritize which training images to collect. This approach assumes that objects in images are labeled with high accuracy. To generate accurate labels in the field, we exploit the spatio-temporal coherence of vehicle video. We use a near-to-far l…
Neural 3D Object Reconstruction with Small-Scale Unmanned Aerial Vehicles
i2CAT Foundation（i2CAT基金会）；University of Klagenfurt（克雷格弗特大学）；Universitat Politècnica de Catalunya（巴塞罗那理工大学）；Faculty of Electrical Engineering and Computing（电气工程与计算学院）；University of Zagreb（扎格雷布大学）；NEC Labs Europe GmbH（NEC欧洲实验室）；ICREA
3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis
Shanghai Jiao Tong University（上海交通大学）；Academy of Military Science（军事科学院）；The University of Sydney（悉尼大学）；College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机学院）
Institute of Mathematic and Computer Science, University of São Paulo（圣保罗大学数学与计算机科学学院）；Computer Science College, Federal University of Uberlândia（乌贝兰迪亚联邦大学计算机科学学院）
Robust perception systems are essential for autonomous vehicle safety. To navigate in a complex urban environment, it is necessary precise sensors with reliable data. The task of understanding the surroundings is hard by itself; for intelligent vehicles, it is even more critical due to the high speed in which the vehicle navigates. To successfully navigate in an urban environment, the perception system must quickly receive, process, and execute an action to guarantee both passenger and pedestrian safety. Stereo cameras collect environment information at many levels, e.g., depth, color, texture…
The Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
Aerial vehicles are revolutionizing applications that require capturing the 3D structure of dynamic targets in the wild, such as sports, medicine, and entertainment. The core challenges in developing a motion-capture system that operates in outdoors environments are: (1) 3D inference requires multiple simultaneous viewpoints of the target, (2) occlusion caused by obstacles is frequent when tracking moving targets, and (3) the camera and vehicle state estimation is noisy. We present a real-time aerial system for multi-camera control that can reconstruct human motions in natural environments wit…
Anomaly detection from a driver's perspective when driving is important to autonomous vehicles. As a part of Advanced Driver Assistance Systems (ADAS), it can remind the driver about dangers timely. Compared with traditional studied scenes such as the university campus and market surveillance videos, it is difficult to detect abnormal event from a driver's perspective due to camera waggle, abidingly moving background, drastic change of vehicle velocity, etc. To tackle these specific problems, this paper proposes a spatial localization constrained sparse coding approach for anomaly detection in…
3D recovery from multi-stereo and stereo images, as an important application of the image-based perspective geometry, serves many applications in computer vision, remote sensing and Geomatics. In this chapter, the authors utilize the imaging geometry and present approaches that perform 3D reconstruction from cross-view images that are drastically different in their viewpoints. We introduce our framework that takes ground-view images and satellite images for full 3D recovery, which includes necessary methods in satellite and ground-based point cloud generation from images, 3D data co-registrati…
Deep Learning (DL) based methods for magnetic resonance (MR) image reconstruction have been shown to produce superior performance in recent years. However, these methods either only leverage under-sampled data or require a paired fully-sampled auxiliary modality to perform multi-modal reconstruction. Consequently, existing approaches neglect to explore attention mechanisms that can transfer textures from reference fully-sampled data to under-sampled data within a single modality, which limits these approaches in challenging cases. In this paper, we propose a novel Texture Transformer Module (T…
The problem of minimization of the number of measurements needed for digital image acquisition and reconstruction with a given accuracy is addressed. Basics of the sampling theory are outlined to show that the lower bound of signal sampling rate sufficient for signal reconstruction with a given accuracy is equal to the spectrum sparsity of the signal sparse approximation that has this accuracy. It is revealed that the compressed sensing approach, which was advanced as a solution to the sampling rate minimization problem, is far from reaching the sampling rate theoretical minimum. Potentials an…
Peking University（北京大学）；Academy for Advanced Interdisciplinary Studies（前沿交叉学科研究院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
We propose a novel and unified method, measurement-conditioned denoising diffusion probabilistic model (MC-DDPM), for under-sampled medical image reconstruction based on DDPM. Different from previous works, MC-DDPM is defined in measurement domain (e.g. k-space in MRI reconstruction) and conditioned on under-sampling mask. We apply this method to accelerate MRI reconstruction and the experimental results show excellent performance, outperforming full supervision baseline and the state-of-the-art score-based reconstruction method. Due to its generative nature, MC-DDPM can also quantify the unce…
Hubei University of Technology（湖北工业大学）；Central China Normal University（华中师范大学）
Most Deep Learning (DL) based Compressed Sensing (DCS) algorithms adopt a single neural network for signal reconstruction, and fail to jointly consider the influences of the sampling operation for reconstruction. In this paper, we propose unified framework, which jointly considers the sampling and reconstruction process for image compressive sensing based on well-designed cascade neural networks. Two sub-networks, which are the sampling sub-network and the reconstruction sub-network, are included in the proposed framework. In the sampling sub-network, an adaptive full connected layer instead o…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；The University of Tokyo（东京大学）；Line Corporation（Line公司）
Estimating the pose of an unmanned aerial vehicle (UAV) or drone is a challenging task. It is useful for many applications such as navigation, surveillance, tracking objects on the ground, and 3D reconstruction. In this work, we present a LiDAR-camera-based relative pose estimation method between a drone and a ground vehicle, using a LiDAR sensor and a fisheye camera on the vehicle's roof and another fisheye camera mounted under the drone. The LiDAR sensor directly observes the drone and measures its position, and the two cameras estimate the relative orientation using indirect observation of …
Technion - Israel Institute of Technology（以色列理工学院）
Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An emerging technology, based on solid-state depth sensors, with no mechanical parts, allows fast, adaptive, programmable scans. In this paper, we investigate the topic of adaptive, image-driven, sampling and reconstruction strategies. First, we formulate a piece-wise linear depth model with several tolerance parameters and estimate its validity for indoor and outdoo…
Modern MRI schemes, which rely on compressed sensing or deep learning algorithms to recover MRI data from undersampled multichannel Fourier measurements, are widely used to reduce scan time. The image quality of these approaches is heavily dependent on the sampling pattern. We introduce a continuous strategy to jointly optimize the sampling pattern and network parameters. We use a multichannel forward model, consisting of a non-uniform Fourier transform with continuously defined sampling locations, to realize the data consistency block within a model-based deep learning image reconstruction sc…
