In this paper, we address the problem of detecting 3D objects from multi-view images. Current query-based methods rely on global 3D position embeddings (PE) to learn the geometric correspondence between images and 3D space. We claim that directly interacting 2D image features with global 3D PE could increase the difficulty of learning view transformation due to the variation of camera extrinsics. Thus we propose a novel method based on CAmera view Position Embedding, called CAPE. We form the 3D position embeddings under the local camera-view coordinate system instead of the global coordinate system, such that 3D position embedding is free of encoding camera extrinsic parameters. Furthermore, we extend our CAPE to temporal modeling by exploiting the object queries of previous frames and encoding the ego-motion for boosting 3D object detection. CAPE achieves state-of-the-art performance (61.0% NDS and 52.5% mAP) among all LiDAR-free methods on nuScenes dataset. Codes and models are available on \href{https://github.com/PaddlePaddle/Paddle3D}{Paddle3D} and \href{https://github.com/kaixinbear/CAPE}{PyTorch Implementation}.
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.
Apple（苹果公司）；Facebook AI Research（Facebook 人工智能研究院）；Herophilus, Inc.（Herophilus 公司）
Without positional information, attention-based Transformer neural networks are permutation-invariant. Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information. Absolute positional embeddings are simple to implement, but suffer from generalization issues when evaluating on sequences longer than seen at training time. Relative positions are more robust to input length change, but are more complex to implement and yield inferior model throughput due to extra computational and memory costs. In this paper, we propose an augmentatio…
This paper presents CAPE, a method to extract planes and cylinder segments from organized point clouds, which processes 640x480 depth images on a single CPU core at an average of 300 Hz, by operating on a grid of planar cells. While, compared to state-of-the-art plane extraction, the latency of CAPE is more consistent and 4-10 times faster, depending on the scene, we also demonstrate empirically that applying CAPE to visual odometry can improve trajectory estimation on scenes made of cylindrical surfaces (e.g. tunnels), whereas using a plane extraction approach that is not curve-aware deterior…
We present cross-view transformers, an efficient attention-based model for map-view semantic segmentation from multiple cameras. Our architecture implicitly learns a mapping from individual camera views into a canonical map-view representation using a camera-aware cross-view attention mechanism. Each camera uses positional embeddings that depend on its intrinsic and extrinsic calibration. These embeddings allow a transformer to learn the mapping across different views without ever explicitly modeling it geometrically. The architecture consists of a convolutional image encoder for each view and…
We introduce a method for 3D object detection using a single monocular image. Starting from a synthetic dataset, we pre-train an RGB-to-Depth Auto-Encoder (AE). The embedding learnt from this AE is then used to train a 3D Object Detector (3DOD) CNN which is used to regress the parameters of 3D object poses after the encoder from the AE generates a latent embedding from the RGB image. We show that we can pre-train the AE using paired RGB and depth images from simulation data once and subsequently only train the 3DOD network using real data, comprising of RGB images and 3D object pose labels (wi…
In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which utilizes the temporal information of previous frames to boost 3D object detection. More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling. The 3D PE achieves the temporal alignment on object position of different frames. A feature-guided position encoder is further introduced to improve the data adaptability of 3D PE. To support for multi-task learning (e.g., BEV segmentation and 3D lan…
University of Oxford（牛津大学）；Visual Geometry Group（视觉几何组）；Department of Engineering Science（工程科学系）
In this paper we propose a geometry-aware model for video object detection. Specifically, we consider the setting that cameras can be well approximated as static, e.g. in video surveillance scenarios, and scene pseudo depth maps can therefore be inferred easily from the object scale on the image plane. We make the following contributions: First, we extend the recent anchor-free detector (CornerNet [17]) to video object detections. In order to exploit the spatial-temporal information while maintaining high efficiency, the proposed model accepts video clips as input, and only makes predictions f…
Monitoring wildlife through camera traps produces a massive amount of images, whose a significant portion does not contain animals, being later discarded. Embedding deep learning models to identify animals and filter these images directly in those devices brings advantages such as savings in the storage and transmission of data, usually resource-constrained in this type of equipment. In this work, we present a comparative study on animal recognition models to analyze the trade-off between precision and inference latency on edge devices. To accomplish this objective, we investigate classifiers …
National Taiwan University（国立台湾大学）；Mobile Drive Technology（移动驱动技术公司）
To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches. However, due to the lack of accurate estimated depth, existing multi-camera methods often generate multiple bounding boxes along a ray of depth direction for difficult small objects such as pedestrians, resulting in an extremely low recall. Furthermore, directly applying depth prediction modules to existing multi-camera methods, generally composed of large network architectures, cannot meet the real-time requirement…
Retrieving accurate semantic information in challenging high dynamic range (HDR) and high-speed conditions remains an open challenge for image-based algorithms due to severe image degradations. Event cameras promise to address these challenges since they feature a much higher dynamic range and are resilient to motion blur. Nonetheless, semantic segmentation with event cameras is still in its infancy which is chiefly due to the lack of high-quality, labeled datasets. In this work, we introduce ESS (Event-based Semantic Segmentation), which tackles this problem by directly transferring the seman…
CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所人机混合增强智能全国重点实验室）；Intelligent Transportation Thrust of the Systems Hub, HKUST(GZ)（香港科技大学（广州）系统枢纽智能交通学域）；Amazon Alexa AI（亚马逊Alexa人工智能）
In this paper we tackle the problem of vehicle re-identification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. Most successful approaches for re-identification involve (deep) learning an embedding space such that the vehicles of s…
University of California, Riverside（加州大学河滨分校）；University of Massachusetts, Lowell（马萨诸塞大学洛厄尔分校）
While most existing video summarization approaches aim to extract an informative summary of a single video, we propose a novel framework for summarizing multi-view videos by exploiting both intra- and inter-view content correlations in a joint embedding space. We learn the embedding by minimizing an objective function that has two terms: one due to intra-view correlations and another due to inter-view correlations across the multiple views. The solution can be obtained directly by solving one Eigen-value problem that is linear in the number of multi-view videos. We then employ a sparse represe…
Midea Robozone Inc（美的机器人公司）；Massachusetts Institute of Technology（麻省理工学院）
Camera relocalization is the key component of simultaneous localization and mapping (SLAM) systems. This paper proposes a learning-based approach, named Sparse Spatial Scene Embedding with Graph Neural Networks (S3E-GNN), as an end-to-end framework for efficient and robust camera relocalization. S3E-GNN consists of two modules. In the encoding module, a trained S3E network encodes RGB images into embedding codes to implicitly represent spatial and semantic embedding code. With embedding codes and the associated poses obtained from a SLAM system, each image is represented as a graph node in a p…
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子通信研究院）
In this paper, we propose a novel framework for multi-target multi-camera tracking (MTMCT) of vehicles based on metadata-aided re-identification (MA-ReID) and the trajectory-based camera link model (TCLM). Given a video sequence and the corresponding frame-by-frame vehicle detections, we first address the isolated tracklets issue from single camera tracking (SCT) by the proposed traffic-aware single-camera tracking (TSCT). Then, after automatically constructing the TCLM, we solve MTMCT by the MA-ReID. The TCLM is generated from camera topological configuration to obtain the spatial and tempora…
School of Data and Computer Science, Sun Yat-sen University（中山大学数据与计算机学院）；Guangdong Province Key Laboratory of Information Security, China（广东省信息安全重点实验室）；School of Electronics and Information Technology, Sun Yat-sen University（中山大学电子与信息工程学院）；Collaborative Innovation Center of High Performance Computing, NUDT（国防科技大学高性能计算协同创新中心）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（教育部机器智能与先进计算重点实验室）
Person re-identification (Re-ID) aims to match identities across non-overlapping camera views. Researchers have proposed many supervised Re-ID models which require quantities of cross-view pairwise labelled data. This limits their scalabilities to many applications where a large amount of data from multiple disjoint camera views is available but unlabelled. Although some unsupervised Re-ID models have been proposed to address the scalability problem, they often suffer from the view-specific bias problem which is caused by dramatic variances across different camera views, e.g., different illumi…
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University（清华大学计算机科学与技术系、人工智能研究院、BNRist中心、THBI实验室、清华-博世联合机器学习中心、清华大学）；Gaoling School of Artificial Intelligence, Renmin University of China（北京人民大学人工智能学院）；National University of Singapore（新加坡国立大学）；Peking University（北京大学）；School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）
Most traditional video summarization methods are designed to generate effective summaries for single-view videos, and thus they cannot fully exploit the complicated intra and inter-view correlations in summarizing multi-view videos in a camera network. In this paper, with the aim of summarizing multi-view videos, we introduce a novel unsupervised framework via joint embedding and sparse representative selection. The objective function is two-fold. The first is to capture the multi-view correlations via an embedding, which helps in extracting a diverse set of representatives. The second is to u…
Rhodes University（罗德斯大学）；University of Ngaoundéré（恩冈代雷大学）
In South Africa, it is a common practice for people to leave their vehicles beside the road when traveling long distances for a short comfort break. This practice might increase human encounters with wildlife, threatening their security and safety. Here we intend to create awareness about wildlife fencing, using drone technology and computer vision algorithms to recognize and detect wildlife fences and associated features. We collected data at Amakhala and Lalibela private game reserves in the Eastern Cape, South Africa. We used wildlife electric fence data containing single and double fences …
Surveillance cameras are widely applied for indoor occupancy measurement and human movement perception, which benefit for building energy management and social security. To address the challenges of limited view angle of single camera as well as lacking of inter-camera collaboration, this study presents a non-overlapping multi-camera system to enlarge the surveillance area and devotes to retrieve the same person appeared from different camera views. The system is deployed in an office building and four-day videos are collected. By training a deep convolutional neural network, the proposed syst…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
By replacing the lens with a thin optical element, lensless imaging enables new applications and solutions beyond those supported by traditional camera design and post-processing, e.g. compact and lightweight form factors and visual privacy. The latter arises from the highly multiplexed measurements of lensless cameras, which require knowledge of the imaging system to recover a recognizable image. In this work, we exploit this unique multiplexing property: casting the optics as an encoder that produces learned embeddings directly at the camera sensor. We do so in the context of image classific…
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）
Despite Neural Radiance Fields (NeRF) showing compelling results in photorealistic novel views synthesis of real-world scenes, most existing approaches require accurate prior camera poses. Although approaches for jointly recovering the radiance field and camera pose exist (BARF), they rely on a cumbersome coarse-to-fine auxiliary positional embedding to ensure good performance. We present Gaussian Activated neural Radiance Fields (GARF), a new positional embedding-free neural radiance field architecture - employing Gaussian activations - that outperforms the current state-of-the-art in terms o…
Most video person re-identification (re-ID) methods are mainly based on supervised learning, which requires cross-camera ID labeling. Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to apply the re-identification algorithm to a large camera network. In this paper, we address the scalability issue by presenting deep representation learning without ID information across multiple cameras. Technically, we train neural networks to generate both ID-discriminative and camera-invariant features. To achieve the ID discrimination ability of the embed…
University of Electronic Science and Technology of China（电子科技大学）
Person re-identification (ReID) is a challenging crosscamera retrieval task to identify pedestrians. Many complex network structures are proposed recently and many of them concentrate on multi-branch features to achieve high performance. However, they are too heavy-weight to deploy in realworld applications. Additionally, pedestrian images are often captured by different surveillance cameras, so the varied lights, perspectives and resolutions result in inevitable multi-camera domain gaps for ReID. To address these issues, this paper proposes ATCN, a simple but effective angular triplet loss-ba…
Google Research（谷歌研究院）；California Institute of Technology（加州理工学院）；Rutgers University（罗格斯大学）
Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people. However, cameras generally capture human poses in 2D as images and videos, which can have significant appearance variations across viewpoints that make the recognition tasks challenging. To address this, we explore recognizing similarity in 3D human body poses from 2D information, which has not been well-studied in existing works. Here, we propose an approach to learning a compact view-invariant embedding space from 2D body joint keypoints, without explicitly predicting 3D poses. Input am…
KIT – University of the State of Baden-Wuerttemberg and National Laboratory of the Helmholtz Association（卡尔斯鲁厄理工学院——巴登-符腾堡州立大学暨亥姆霍兹协会国家实验室）
Person re-identification (re-id) is the task of recognizing and matching persons at different locations recorded by cameras with non-overlapping views. One of the main challenges of re-id is the large variance in person poses and camera angles since neither of them can be influenced by the re-id system. In this work, an effective approach to integrate coarse camera view information as well as fine-grained pose information into a convolutional neural network (CNN) model for learning discriminative re-id embeddings is introduced. In most recent work pose information is either explicitly modeled …
WYZE Labs AI Team（WYZE实验室人工智能团队）；University of Washington（华盛顿大学）
Package theft detection has been a challenging task mainly due to lack of training data and a wide variety of package theft cases in reality. In this paper, we propose a new Global and Local Fusion Package Theft Detection Embedding (GLF-PTDE) framework to generate package theft scores for each segment within a video to fulfill the real-world requirements on package theft detection. Moreover, we construct a novel Package Theft Detection dataset to facilitate the research on this task. Our method achieves 80% AUC performance on the newly proposed dataset, showing the effectiveness of the propose…
Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose information of the person to learn a discriminative embedding. In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective repres…
Utilizing the sensor characteristics of the audio, visible camera, and thermal camera, the robustness of person recognition can be enhanced. Existing multimodal person recognition frameworks are primarily formulated assuming that multimodal data is always available. In this paper, we propose a novel trimodal sensor fusion framework using the audio, visible, and thermal camera, which addresses the missing modality problem. In the framework, a novel deep latent embedding framework, termed the AVTNet, is proposed to learn multiple latent embeddings. Also, a novel loss function, termed missing mod…
University of Quebec at Montreal（魁北克大学蒙特利尔分校）；University of Bahrain（巴林大学）
We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment. Previous approaches built a scene-dependent model that explicitly or implicitly embeds the structure of the scene. They use convolution neural networks or decision trees to establish 2D/3D-3D correspondences. Such a mapping overfits the target scene and does not generalize well to dynamic changes in the environment. Our work introduces a novel approach to solve the camera relocalization problem by using the available triang…
