Inferring object 3D position and orientation from a single RGB camera is a foundational task in computer vision with many important applications. Traditionally, 3D object detection methods are trained in a fully-supervised setup, requiring LiDAR and vast amounts of human annotations, which are laborious, costly, and do not scale well with the ever-increasing amounts of data being captured.
We present a novel method to train a 3D object detector from a single RGB camera without domain-specific human annotations, making orders of magnitude more data available for training. The method uses newly proposed Local Object Motion Model to disentangle object movement source between subsequent frames, is approximately 700 times faster than previous work and compensates camera focal length differences to aggregate multiple datasets.
The method is evaluated on three public datasets, where despite using no human labels, it outperforms prior work by a significant margin. It also shows its versatility as a pre-training tool for fully-supervised training and shows that combining pseudo-labels from multiple datasets can achieve comparable accuracy to using human labels from a single dataset. The source code and model are available at https://github.com/jskvrna/MonoSOWA.
Amazon Lab126（亚马逊Lab126）；University of Washington（华盛顿大学）
To improve the generalization of 3D human pose estimators, many existing deep learning based models focus on adding different augmentations to training poses. However, data augmentation techniques are limited to the "seen" pose combinations and hard to infer poses with rare "unseen" joint positions. To address this problem, we present CameraPose, a weakly-supervised framework for 3D human pose estimation from a single image, which can not only be applied on 2D-3D pose pairs but also on 2D alone annotations. By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our…
PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection
Korea Institute of Science and Technology (KIST)（韩国科学技术研究院）；KAIST AI（韩国科学技术院人工智能系）；VRG, FEE, Czech Technical University in Prague（布拉格捷克理工大学电气工程学院视觉识别组）；Samsung Research（三星研究院）；AI-Robotics, KIST School, University of Science and Technology (UST)（科学技术联合大学院KIST学院人工智能机器人系）；Yonsei-KIST Convergence Research Institute, Yonsei University（延世大学延世-KIST融合研究院）
CVLab, EPFL（瑞士联邦理工学院计算机视觉实验室）；Balgrist University Hospital（巴尔格里斯特大学医院）；University of Salzburg（萨尔茨堡大学）；UNIL（洛桑大学）
Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such database exists. Manual annotation is tedious, slow, and error-prone. In this paper, we propose to replace most of the annotations by the use of multiple views, at training time only. Specifically, we train the system to predict the same pose in all views. Such a consistency constraint is necessary but not sufficient to predict accurate poses. We therefore comp…
Monocular 3D object detection is one of the most challenging tasks in 3D scene understanding. Due to the ill-posed nature of monocular imagery, existing monocular 3D detection methods highly rely on training with the manually annotated 3D box labels on the LiDAR point clouds. This annotation process is very laborious and expensive. To dispense with the reliance on 3D box labels, in this paper we explore the weakly supervised monocular 3D detection. Specifically, we first detect 2D boxes on the image. Then, we adopt the generated 2D boxes to select corresponding RoI LiDAR points as the weak sup…
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we propose a differentiable forward rigid projection module that plays a key role in our instance-wise depth and motion learning. Second, we design an instance-wise photometric and geometric consistency loss that effectively decomposes background and moving object regions. Lastly, we introduce a new auto-annotation scheme to produce video instance segmentation m…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Indian Institute of Technology（印度理工学院）；Axogyan AI（Axogyan人工智能公司）
Monocular 3D human-pose estimation from static images is a challenging problem, due to the curse of dimensionality and the ill-posed nature of lifting 2D-to-3D. In this paper, we propose a Deep Conditional Variational Autoencoder based model that synthesizes diverse anatomically plausible 3D-pose samples conditioned on the estimated 2D-pose. We show that CVAE-based 3D-pose sample set is consistent with the 2D-pose and helps tackling the inherent ambiguity in 2D-to-3D lifting. We propose two strategies for obtaining the final 3D pose- (a) depth-ordering/ordinal relations to score and weight-ave…
University of Michigan（密歇根大学）；DROP lab（DROP实验室）；Department of Naval Architecture and Marine Engineering（船舶与海洋工程系）
There has been much recent interest in deep learning methods for monocular image based object pose estimation. While object pose estimation is an important problem for autonomous robot interaction with the physical world, and the application space for monocular-based methods is expansive, there has been little work on applying these methods with fisheye imaging systems. Also, little exists in the way of annotated fisheye image datasets on which these methods can be developed and tested. The research landscape is even more sparse for object detection methods applied in the underwater domain, fi…
WildLIFT: Lifting monocular drone video to 3D for species-agnostic wildlife monitoring
Fondazione Bruno Kessler（布雷诺·科塞勒基金会）；University of Muenster（明斯特大学）；Max Planck Institute of Animal Behaviour（动物行为马克斯·普朗克研究所）；University of Konstanz（康斯坦茨大学）
University of Genoa（热那亚大学）；Technical University of Munich（慕尼黑工业大学）；Google Inc.（谷歌公司）
Monocular 3D object detection continues to attract attention due to the cost benefits and wider availability of RGB cameras. Despite the recent advances and the ability to acquire data at scale, annotation cost and complexity still limit the size of 3D object detection datasets in the supervised settings. Self-supervised methods, on the other hand, aim at training deep networks relying on pretext tasks or various consistency constraints. Moreover, other 3D perception tasks (such as depth estimation) have shown the benefits of temporal priors as a self-supervision signal. In this work, we argue…
Tsinghua University（清华大学）；Massachusetts Institute of Technology（麻省理工学院）；Microsoft Research（微软研究院）
Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regress…
Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）；Dalian University of Technology（大连理工大学）；The Hong Kong University of Science and Technology（香港科技大学）
Cooperative Medianet Innovation Center (CMIC)（合作 medianet 创新中心（CMIC））；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；Shanghai AI Laboratory（上海人工智能实验室）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasible to provide 2D joint annotations for large corpora of in-the-wild images with humans, providing accurate 3D annotations to such in-the-wild corpora is hardly feasible in practice. Most existing 3D labelled data sets are either synthetically created or feature in-studio images. 3D pose estimation algorithms trained on such data often have limited ability to generalize to real world scene diversity. We therefore propo…
Purdue University（普渡大学）；Curtin University（科廷大学）；University of Hawaii Cancer Center（夏威夷大学癌症中心）
We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting. Specifically, we are interested in end-to-end estimation of food portion size, which has great potential in the field of personal health management. Unlike image segmentation or object recognition where annotation can be obtained through large scale crowd sourcing, it is much more challenging to collect datasets for portion size estimation since human cannot accurately estimate the size of an object in an arbitrary 2D image …
Institute of Intelligent Vehicles, School of Automotive Studies, Tongji University（同济大学汽车学院智能车辆研究所）
Object localization in 3D space is a challenging aspect in monocular 3D object detection. Recent advances in 6DoF pose estimation have shown that predicting dense 2D-3D correspondence maps between image and object 3D model and then estimating object pose via Perspective-n-Point (PnP) algorithm can achieve remarkable localization accuracy. Yet these methods rely on training with ground truth of object geometry, which is difficult to acquire in real outdoor scenes. To address this issue, we propose MonoRUn, a novel detection framework that learns dense correspondences and geometry in a self-supe…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Nanyang Technological University（南洋理工大学）；The Chinese University of Hong Kong（香港中文大学）；Hong Kong University of Science and Technology（香港科技大学）
In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022. For multi-view camera-only 3D detection, methods based on bird-eye-view or 3D geometric representations can leverage the stereo cues from overlapped regions between adjacent views and directly perform 3D detection without hand-crafted post-processing. However, it lacks direct semantic supervision for 2D backbones, which can be complemented by pretraining simple monocular-based detectors. Our solution is a multi-view framework for 4D detection follo…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Hyundai Motor Company（现代汽车公司）；Hanyang University（汉阳大学）
Recent advances in monocular 3D detection leverage a depth estimation network explicitly as an intermediate stage of the 3D detection network. Depth map approaches yield more accurate depth to objects than other methods thanks to the depth estimation network trained on a large-scale dataset. However, depth map approaches can be limited by the accuracy of the depth map, and sequentially using two separated networks for depth estimation and 3D detection significantly increases computation cost and inference time. In this work, we propose a method to boost the RGB image-based 3D detector by joint…
Tsinghua University（清华大学）；University of Michigan（密歇根大学）
Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human annotations, we propose Mix-Teaching, an effective semi-supervised learning framework applicable to employ both labeled and unlabeled images in training stage. Mix-Teaching first generates pseudo-labels for unlabeled images by self-training. The student model is then trained on the mixed images possessing much more intensive and precise labeling by merging i…
Monocular 2D Camera-based Proximity Monitoring for Human-Machine Collision Warning on Construction Sites
City University of Hong Kong（香港城市大学）；Architecture and Civil Engineering Research Center, Shenzhen Research Institute of City University of Hong Kong（香港城市大学深圳研究院建筑与土木工程研究中心）
Vanishing points (VPs) play a vital role in various computer vision tasks, especially for recognizing the 3D scenes from an image. In the real-world scenario of automobile applications, it is costly to manually obtain the external camera parameters when the camera is attached to the vehicle or the attachment is accidentally perturbed. In this paper we introduce a simple but effective end-to-end vanishing point detection. By automatically calculating intersection of the extrapolated lane marker annotations, we obtain geometrically consistent VP labels and mitigate human annotation errors caused…
Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学北京信息科学与技术国家研究中心）；School of Software, Tsinghua University（清华大学软件学院）；Aberystwyth University（阿伯里斯特威斯大学）
The ground plane prior is a very informative geometry clue in monocular 3D object detection (M3OD). However, it has been neglected by most mainstream methods. In this paper, we identify two key factors that limit the applicability of ground plane prior: the projection point localization issue and the ground plane tilt issue. To pick up the ground plane prior for M3OD, we propose a Ground Plane Enhanced Network (GPENet) which resolves both issues at one go. For the projection point localization issue, instead of using the bottom vertices or bottom center of the 3D bounding box (BBox), we levera…
Weakly Supervised Monocular 3D Detection with a Single-View Image
Nanyang Technological University（南洋理工大学）；Sensetime Research（商汤科技研究院）；College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）
Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detection
Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）；Xi'an Jiaotong University（西安交通大学）；Intelligent Transportation Thrust of the Systems Hub（系统枢纽智能交通事业部）；Hong Kong University of Science and Technology (GZ)（香港科技大学（广州））；Amazon Alexa AI（亚马逊Alexa AI）
IIT Bombay（印度理工学院孟买分校）；Axogyan AI（Axogyan人工智能公司）；IISc Bangalore（印度科学学院班加罗尔分校）；University of California, San Diego（加州大学圣地亚哥分校）
The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal re…
Insufficient labeled training datasets is one of the bottlenecks of 3D hand pose estimation from monocular RGB images. Synthetic datasets have a large number of images with precise annotations, but the obvious difference with real-world datasets impacts the generalization. Little work has been done to bridge the gap between two domains over their wide difference. In this paper, we propose a domain adaptation method called Adaptive Wasserstein Hourglass (AW Hourglass) for weakly-supervised 3D hand pose estimation, which aims to distinguish the difference and explore the common characteristics (…
Technical University of Munich（慕尼黑工业大学）；Tsinghua University（清华大学）；Google（谷歌）
6D object pose estimation is a fundamental problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even from monocular images. Nonetheless, CNNs are identified as being extremely data-driven, and acquiring adequate annotations is oftentimes very time-consuming and labor intensive. To overcome this shortcoming, we propose the idea of monocular 6D pose estimation by means of self-supervised learning, removing the need for real annotations. After training our proposed network fully supervised with synthetic RGB d…
In this paper, we propose 3DBodyTex.Pose, a dataset that addresses the task of 3D human pose estimation in-the-wild. Generalization to in-the-wild images remains limited due to the lack of adequate datasets. Existent ones are usually collected in indoor controlled environments where motion capture systems are used to obtain the 3D ground-truth annotations of humans. 3DBodyTex.Pose offers high quality and rich data containing 405 different real subjects in various clothing and poses, and 81k image samples with ground-truth 2D and 3D pose annotations. These images are generated from 200 viewpoin…
Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving. However, depth completion faces 3 main challenges: the irregularly spaced pattern in the sparse depth input, the difficulty in handling multiple sensor modalities (when color images are available), as well as the lack of dense, pixel-level ground truth depth labels. In this work, we address all these challenges. Specifically, we develop a deep regression model to learn a direct mapping from sparse depth (and color images) to dense d…
University of Freiburg（弗莱堡大学）；Federal University of Rio Grande（里奥格兰德联邦大学）；University of Technology Nuremberg（纽伦堡工业大学）
Bird's-Eye-View (BEV) semantic maps have become an essential component of automated driving pipelines due to the rich representation they provide for decision-making tasks. However, existing approaches for generating these maps still follow a fully supervised training paradigm and hence rely on large amounts of annotated BEV data. In this work, we address this limitation by proposing the first self-supervised approach for generating a BEV semantic map using a single monocular image from the frontal view (FV). During training, we overcome the need for BEV ground truth annotations by leveraging …
Advances in Deep Learning have recently made it possible to recover full 3D meshes of human poses from individual images. However, extension of this notion to videos for recovering temporally coherent poses still remains unexplored. A major challenge in this regard is the lack of appropriately annotated video data for learning the desired deep models. Existing human pose datasets only provide 2D or 3D skeleton joint annotations, whereas the datasets are also recorded in constrained environments. We first contribute a technique to synthesize monocular action videos with rich 3D annotations that…
We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space. Conventional 2D lane detection from a monocular image yields poor performance of following planning and control tasks in autonomous driving due to the case of uneven road. Predicting the 3D lane layout is thus necessary and enables effective and safe driving. However, existing 3D lane detection datasets are either unpublished or synthesized from a simulated environment, severely hampering the development of this field. In this paper, we take steps towards addressing these issues. By exploi…
Moving6DPoSe: A Multimodal Database for Monocular 6D Pose Estimation and Segmentation of Moving Objects
University of Chile（智利大学）；Advanced Mining Technology Center (AMTC), University of Chile（智利大学先进采矿技术中心）；The Iniciativa de Datos e Inteligencia Artificial, University of Chile（智利大学数据与人工智能计划）
Monocular 3D object detection is a challenging task in the self-driving and computer vision community. As a common practice, most previous works use manually annotated 3D box labels, where the annotating process is expensive. In this paper, we find that the precisely and carefully annotated labels may be unnecessary in monocular 3D detection, which is an interesting and counterintuitive finding. Using rough labels that are randomly disturbed, the detector can achieve very close accuracy compared to the one using the ground-truth labels. We delve into this underlying mechanism and then empirica…
Technical University of Munich（慕尼黑工业大学）；Tsinghua University（清华大学）；Toyota Motor Europe（丰田汽车欧洲）
Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally hampers possible applications as, for instance, robots seamlessly integrated in everyday processes necessarily require the ability to work with hundreds of different objects. To tackle this problem of immanent practical relevance, we propose a novel method for class-level monocular 6D pose estimation, coupled with metric shape retrieval. Unfortunately, acquiring adequate annotations is very time-consuming and labor intensive. This is especially true for class-level 6D pose estimat…
Monocular 3D vehicle localization is an important task in Intelligent Transportation System (ITS) and Cooperative Vehicle Infrastructure System (CVIS), which is usually achieved by monocular 3D vehicle detection. However, depth information cannot be obtained directly by monocular cameras due to the inherent imaging mechanism, resulting in more challenging monocular 3D tasks. Most of the current monocular 3D vehicle detection methods leverage 2D detectors and additional geometric modules, which reduces the efficiency. In this paper, we propose a 3D vehicle localization network CenterLoc3D for r…
Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation
Advanced Research Center on Electronic System (ARCES)（电子系统先进研究中心）；Department of Computer Science and Engineering (DISI)（计算机科学与工程系）；University of Bologna（博洛尼亚大学）
