Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
Harbin Institute of Technology（哈尔滨工业大学）；Ningbo Institute of Intelligent Equipment Technology Co., Ltd.（宁波智能装备技术有限公司）；Harbin Institute of Technology Robot Innovation Center Co., Ltd.（哈尔滨工业大学机器人创新中心有限公司）；Peng Cheng Laboratory（鹏城实验室）
Tianze Gao, Huihui Pan, Huijun Gao
备注：
11 pages, 11 figures. This paper has been accepted by IEEE Transactions of Intelligent Vehicles. Digital Object Identifier: 10.1109/TIV.2022.3143954
Monocular 3D object detection, with the aim of predicting the geometric properties of on-road objects, is a promising research topic for the intelligent perception systems of autonomous driving. Most state-of-the-art methods follow a keypoint-based paradigm, where the keypoints of objects are predicted and employed as the basis for regressing the other geometric properties. In this work, a unified network named as FADNet is presented to address the task of monocular 3D object detection. In contrast to previous keypoint-based methods, we propose to divide the output modalities into different groups according to the estimation difficulty of object properties. Different groups are treated differently and sequentially associated by a convolutional Gated Recurrent Unit. Another contribution of this work is the strategy of depth hint augmentation. To provide characterized depth patterns as hints for depth estimation, a dedicated depth hint module is designed to generate row-wise features named as depth hints, which are explicitly supervised in a bin-wise manner. The contributions of this work are validated by conducting experiments and ablation study on the KITTI benchmark. Without utilizing depth priors, post optimization, or other refinement modules, our network performs competitively against state-of-the-art methods while maintaining a decent running speed.
The Hong Kong University of Science and Technology（香港科技大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
This paper investigates the geometric consistency for monocular 3D object detection, which suffers from the ill-posed depth estimation. We first conduct a thorough analysis to reveal how existing methods fail to consistently localize objects when different geometric shifts occur. In particular, we design a series of geometric manipulations to diagnose existing detectors and then illustrate their vulnerability to consistently associate the depth with object apparent sizes and positions. To alleviate this issue, we propose four geometry-aware data augmentation approaches to enhance the geometric…
Data augmentation is a key component of CNN based image recognition tasks like object detection. However, it is relatively less explored for 3D object detection. Many standard 2D object detection data augmentation techniques do not extend to 3D box. Extension of these data augmentations for 3D object detection requires adaptation of the 3D geometry of the input scene and synthesis of new viewpoints. This requires accurate depth information of the scene which may not be always available. In this paper, we evaluate existing 2D data augmentations and propose two novel augmentations for monocular …
National Taiwan University（国立台湾大学）；Mobile Drive Technology（移动驱动科技公司）
Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary super…
University of Chinese Academy of Sciences（中国科学院大学）
In this work, we propose a novel single-shot and keypoints-based framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design a fully convolutional model to predict object keypoints, dimension, and orientation, and then combine these estimations with perspective geometry constraints to compute position attribute. Further, we reformulate the geometric constraints as a differentiable version and embed it into the network to reduce running time while maintaining the consistency of model outputs in an end-to-end fashion. Benefiting from this simple structure, we t…
Technical University of Munich（慕尼黑工业大学）；Toyota Research Institute（丰田研究院）
We present a deep learning method for end-to-end monocular 3D object detection and metric shape retrieval. We propose a novel loss formulation by lifting 2D detection, orientation, and scale estimation into 3D space. Instead of optimizing these quantities separately, the 3D instantiation allows to properly measure the metric misalignment of boxes. We experimentally show that our 10D lifting of sparse 2D Regions of Interests (RoIs) achieves great results both for 6D pose and recovery of the textured metric geometry of instances. This further enables 3D synthetic data augmentation via inpainting…
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…
Monocular depth estimators can be trained with various forms of self-supervision from binocular-stereo data to circumvent the need for high-quality laser scans or other ground-truth data. The disadvantage, however, is that the photometric reprojection losses used with self-supervised learning typically have multiple local minima. These plausible-looking alternatives to ground truth can restrict what a regression network learns, causing it to predict depth maps of limited quality. As one prominent example, depth discontinuities around thin structures are often incorrectly estimated by current s…
MPI for Informatics（马克斯·普朗克信息学研究所）；EPFL（洛桑联邦理工学院）；Universidad Rey Juan Carlos（胡安·卡洛斯国王大学）
We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data. Using only the existing 3D pose data and 2D pose data, we show state-of-the-art performance on established benchmarks through transfer of learned features, while also generalizing to in-the-wild scenes. We further introduce a new training set for human body pose estimation from monocular images of real humans that has the ground truth captured with a multi-camera marker-less…
Monocular 3D detection has drawn much attention from the community due to its low cost and setup simplicity. It takes an RGB image as input and predicts 3D boxes in the 3D space. The most challenging sub-task lies in the instance depth estimation. Previous works usually use a direct estimation method. However, in this paper we point out that the instance depth on the RGB image is non-intuitive. It is coupled by visual depth clues and instance attribute clues, making it hard to be directly learned in the network. Therefore, we propose to reformulate the instance depth to the combination of the …
3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
Stanford University（斯坦福大学）；University of Southern California（南加州大学）；Bosch Research North America（博世北美研究院）；Bosch Center for Artificial Intelligence (BCAI)（博世人工智能中心（BCAI））
Harbin Institute of Technology（哈尔滨工业大学）；DiDi Chuxing（滴滴出行）；University of North Texas（北德克萨斯大学）
In this paper, we improve the challenging monocular 3D object detection problem with a general semi-supervised framework. Specifically, having observed that the bottleneck of this task lies in lacking reliable and informative samples to train the detector, we introduce a novel, simple, yet effective `Augment and Criticize' framework that explores abundant informative samples from unlabeled data for learning more robust detection models. In the `Augment' stage, we present the Augmentation-based Prediction aGgregation (APG), which aggregates detections from various automatically learned augmente…
The Hong Kong University of Science and Technology（香港科技大学）；Tencent（腾讯）
End-to-end deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation, yet these models may fail for unseen poses with limited and fixed training data. This paper proposes a novel data augmentation method that: (1) is scalable for synthesizing massive amount of training data (over 8 million valid 3D human poses with corresponding 2D projections) for training 2D-to-3D networks, (2) can effectively reduce dataset bias. Our method evolves a limited dataset to synthesize unseen 3D human skeletons based on a hierarchical human representation and heuristics …
Modern object detection architectures are moving towards employing self-supervised learning (SSL) to improve performance detection with related pretext tasks. Pretext tasks for monocular 3D object detection have not yet been explored yet in literature. The paper studies the application of established self-supervised bounding box recycling by labeling random windows as the pretext task. The classifier head of the 3D detector is trained to classify random windows containing different proportions of the ground truth objects, thus handling the foreground-background imbalance. We evaluate the prete…
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.
Shanghai Jiao Tong University（上海交通大学）；University of Cambridge（剑桥大学）
Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with t…
Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view synthesis, utilising warped photometric consistency. Although it gives good results when trained using stereo data, the predicted depth is still sensitive to noise, illumination changes and specular reflections. Also, occlusion can be tackled better by learning depth from a single camera. We propose ADAA, utilising depth augmentation as depth supervision for learnin…
Korea University（高丽大学）；University of Bologna（博洛尼亚大学）
We propose MaskingDepth, a novel semi-supervised learning framework for monocular depth estimation to mitigate the reliance on large ground-truth depth quantities. MaskingDepth is designed to enforce consistency between the strongly-augmented unlabeled data and the pseudo-labels derived from weakly-augmented unlabeled data, which enables learning depth without supervision. In this framework, a novel data augmentation is proposed to take the advantage of a naive masking strategy as an augmentation, while avoiding its scale ambiguity problem between depths from weakly- and strongly-augmented bra…
ETH Zurich（苏黎世联邦理工学院）；University of Bonn（波恩大学）；KU Leuven（鲁汶大学）
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. In particular, we propose three key contributions: (1) We transfer knowledge from features learned during self-supervised depth estimation to semantic segmentation, (2) we implement a strong data augment…
It is difficult to collect data on a large scale in a monocular depth estimation because the task requires the simultaneous acquisition of RGB images and depths. Data augmentation is thus important to this task. However, there has been little research on data augmentation for tasks such as monocular depth estimation, where the transformation is performed pixel by pixel. In this paper, we propose a data augmentation method, called CutDepth. In CutDepth, part of the depth is pasted onto an input image during training. The method extends variations data without destroying edge features. Experimen…
We consider the task of estimating the 3D orientation of an object of known category given an image of the object and a bounding box around it. Recently, CNN-based regression and classification methods have shown significant performance improvements for this task. This paper proposes a new CNN-based approach to monocular orientation estimation that advances the state of the art in four different directions. First, we take into account the Riemannian structure of the orientation space when designing regression losses and nonlinear activation functions. Second, we propose a mixed Riemannian regr…
Renmin University of China（中国人民大学）；Nanjing University of Science and Technology（南京理工大学）；Nreal；Tsinghua University（清华大学）
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications. In order to relieve this problem, this paper proposes a novel approach named Object Level Depth reconstruction Network (OLD-Net) taking only RGB images as input for category-level 6D object pose estimation. We propose to directly predict object-level depth from a monocular RGB image by deforming the category-level shape prior into object-level depth and the canonical NOCS representation. Two novel modules …
Nanjing University of Science and Technology（南京理工大学）
Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe performance degradation when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions. In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth. Specifically, we propose a simple yet efficient data augmentation method to generate images with arbitrary scales for the same scene. Then,…
Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction. Existing solutions for depth estimation often produce blurry approximations of low resolution. This paper presents a convolutional neural network for computing a high-resolution depth map given a single RGB image with the help of transfer learning. Following a standard encoder-decoder architecture, we leverage features extracted using high performing pre-trained networks when initializing our encoder along with augmentation and training strategies that lead to more…
University of Pittsburgh（匹兹堡大学）；Laboratoire d’Informatique Gaspard Monge - CNRS UMR 8049, Universit$ ´ e $ Paris-Est（加斯帕德·蒙日信息学实验室 - 法国国家科学研究中心联合实验室8049，巴黎东部大学）
Monocular depth estimation, which plays a key role in understanding 3D scene geometry, is fundamentally an ill-posed problem. Existing methods based on deep convolutional neural networks (DCNNs) have examined this problem by learning convolutional networks to estimate continuous depth maps from monocular images. However, we find that training a network to predict a high spatial resolution continuous depth map often suffers from poor local solutions. In this paper, we hypothesize that achieving a compromise between spatial and depth resolutions can improve network training. Based on this "compr…
Rethinking Monocular Depth Embedding for Generalized Stereo Matching
Shaanxi Key Laboratory for Network Computing and Security Technology, Xi’an University of Technology（陕西理工大学网络计算与安全技术重点实验室）；College of Computer Science, Sichuan University（四川大学计算机学院）
We propose a semi-supervised learning framework for monocular depth estimation. Compared to existing semi-supervised learning methods, which inherit limitations of both sparse supervised and unsupervised loss functions, we achieve the complementary advantages of both loss functions, by building two separate network branches for each loss and distilling each other through the mutual distillation loss function. We also present to apply different data augmentation to each branch, which improves the robustness. We conduct experiments to demonstrate the effectiveness of our framework over the lates…
Niantic（Niantic公司）；University of Edinburgh（爱丁堡大学）；University of Oxford（牛津大学）；UCL（伦敦大学学院）
Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also available at test time. The vast majority of monocular networks do not make use of this extra signal, thus ignoring valuable information that could be used to improve the predicted depth. Those that do, either use computationally expensive test-time refinement techniques or off-the-shelf recurrent networks, which only indirectly make use of the geometric inform…
ETH Zurich（苏黎世联邦理工学院）；MPI for Informatics（马克斯·普朗克信息学研究所）；KU Leuven（鲁汶大学）
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised and domain-adaptive semantic segmentation, which is enhanced by self-supervised monocular depth estimation (SDE) trained only on unlabeled image sequences. In particular, we utilize SDE as an auxiliary task comprehensively across the entire learning framework: First, we automatically select the most useful samples to be …
Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and training strategy for monocular depth estimation to further improve the prediction accuracy of the network. We deploy a hierarchical transformer encoder to capture and convey the global context, and design a lightweight yet powerful decoder to generate an estimated depth map while considering local connectivity. By constructing connected paths between multi…
Monocular depth estimation (MDE) in the self-supervised scenario has emerged as a promising method as it refrains from the requirement of ground truth depth. Despite continuous efforts, MDE is still sensitive to scale changes especially when all the training samples are from one single camera. Meanwhile, it deteriorates further since camera movement results in heavy coupling between the predicted depth and the scale change. In this paper, we present a scale-invariant approach for self-supervised MDE, in which scale-sensitive features (SSFs) are detached away while scale-invariant features (SIF…
