Applications in the field of augmented reality or robotics often require joint localisation and 6D pose estimation of multiple objects. However, most algorithms need one network per object class to be trained in order to provide the best results. Analysing all visible objects demands multiple inferences, which is memory and time-consuming. We present a new single-stage architecture called CASAPose that determines 2D-3D correspondences for pose estimation of multiple different objects in RGB images in one pass. It is fast and memory efficient, and achieves high accuracy for multiple objects by exploiting the output of a semantic segmentation decoder as control input to a keypoint recognition decoder via local class-adaptive normalisation. Our new differentiable regression of keypoint locations significantly contributes to a faster closing of the domain gap between real test and synthetic training data. We apply segmentation-aware convolutions and upsampling operations to increase the focus inside the object mask and to reduce mutual interference of occluding objects. For each inserted object, the network grows by only one output segmentation map and a negligible number of parameters. We outperform state-of-the-art approaches in challenging multi-object scenes with inter-object occlusion and synthetic training.
translated by 谷歌翻译
This paper addresses the challenge of 6DoF pose estimation from a single RGB image under severe occlusion or truncation. Many recent works have shown that a two-stage approach, which first detects keypoints and then solves a Perspective-n-Point (PnP) problem for pose estimation, achieves remarkable performance. However, most of these methods only localize a set of sparse keypoints by regressing their image coordinates or heatmaps, which are sensitive to occlusion and truncation. Instead, we introduce a Pixel-wise Voting Network (PVNet) to regress pixel-wise unit vectors pointing to the keypoints and use these vectors to vote for keypoint locations using RANSAC. This creates a flexible representation for localizing occluded or truncated keypoints. Another important feature of this representation is that it provides uncertainties of keypoint locations that can be further leveraged by the PnP solver. Experiments show that the proposed approach outperforms the state of the art on the LINEMOD, Occlusion LINEMOD and YCB-Video datasets by a large margin, while being efficient for real-time pose estimation. We further create a Truncation LINEMOD dataset to validate the robustness of our approach against truncation. The code will be avaliable at https://zju-3dv.github.io/pvnet/.
translated by 谷歌翻译
我们提出了一种称为DPODV2(密集姿势对象检测器)的三个阶段6 DOF对象检测方法,该方法依赖于致密的对应关系。我们将2D对象检测器与密集的对应关系网络和多视图姿势细化方法相结合,以估计完整的6 DOF姿势。与通常仅限于单眼RGB图像的其他深度学习方法不同,我们提出了一个统一的深度学习网络,允许使用不同的成像方式(RGB或DEPTH)。此外,我们提出了一种基于可区分渲染的新型姿势改进方法。主要概念是在多个视图中比较预测并渲染对应关系,以获得与所有视图中预测的对应关系一致的姿势。我们提出的方法对受控设置中的不同数据方式和培训数据类型进行了严格的评估。主要结论是,RGB在对应性估计中表现出色,而如果有良好的3D-3D对应关系,则深度有助于姿势精度。自然,他们的组合可以实现总体最佳性能。我们进行广泛的评估和消融研究,以分析和验证几个具有挑战性的数据集的结果。 DPODV2在所有这些方面都取得了出色的成果,同时仍然保持快速和可扩展性,独立于使用的数据模式和培训数据的类型
translated by 谷歌翻译
最先进的对象姿势估计通过使用多模型公式来处理测试图像中的多个实例:检测作为第一阶段,然后每个对象单独训练的网络,以作为第二阶段的2d-3d几何对应关系预测。随后,使用Perspective-N点算法在运行时估算姿势。不幸的是,多模型配方很慢,并且与所涉及的对象实例的数量相比不能很好地扩展。最近的方法表明,直接6D对象姿势估计是可行的,当时是从上述几何对应关系得出的。我们提出了一种方法,该方法学习了多个对象的中间几何表示,以直接回归测试图像中所有实例的6D姿势。固有的端到端训练性克服了单独处理单个对象实例的要求。通过计算相互关联的联合会,将姿势假设聚集在不同的实例中,从而相对于对象实例的数量实现了可忽略的运行时开销。多个挑战性标准数据集的结果表明,尽管姿势估计的性能快于35倍以上,但姿势估计性能优于单模最先进的方法。我们还提供了一个分析,显示存在90多个对象实例的图像实时适用性(> 24 fps)。进一步的结果表明,用6D姿势监督基于几何相应的对象姿势估计的优势。
translated by 谷歌翻译
我们提出了一种基于相交的球体的新型关键点投票方案,其比现有方案更准确,并且允许较小的更多分散关键点。该方案基于点之间的距离,其作为1D数量可以比在先前的工作中的2D和3D向量和偏移量中更精确地回归,从而产生更准确的小点定位。该方案构成了RGB-D数据中的6 DOF姿势估计的所提出的RCVPOS方法的基础,这在处理闭塞时特别有效。训练CNN以估计与每个RGB像素的深度模式对应的3D点之间的距离,以及在对象帧中定义的一组3分散键点。在推断下,产生在每个3D点处的球体,其半径等于该估计距离。这些球体的表面投票给增量3D累加器空间,其峰值指示Keypoint位置。所提出的径向投票方案比以前的矢量或偏移方案更准确,并且稳健地分散关键点。实验表明,RCPOSE是高度准确和竞争的,在LineMod 99.7%和YCB-Video 97.2%数据集上实现最先进的结果,显着得分+ 7.9%(71.1%)比以前的挑战遮挡Linemod上的方法数据集。
translated by 谷歌翻译
Estimating 6D poses of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the input image can produce accurate results. In this work, we propose a novel deep neural network for 6D pose matching named DeepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using a disentangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks for 6D pose estimation demonstrate that DeepIM achieves large improvements over stateof-the-art methods. We furthermore show that DeepIM is able to match previously unseen objects.
translated by 谷歌翻译
We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. Unlike a recently proposed single-shot technique for this task [11] that only predicts an approximate 6D pose that must then be refined, ours is accurate enough not to require additional post-processing. As a result, it is much faster -50 fps on a Titan X (Pascal) GPU -and more suitable for real-time processing. The key component of our method is a new CNN architecture inspired by [28,29] that directly predicts the 2D image locations of the projected vertices of the object's 3D bounding box. The object's 6D pose is then estimated using a PnP algorithm.For single object and multiple object pose estimation on the LINEMOD and OCCLUSION datasets, our approach substantially outperforms other recent 26] when they are all used without postprocessing. During post-processing, a pose refinement step can be used to boost the accuracy of these two methods, but at 10 fps or less, they are much slower than our method.
translated by 谷歌翻译
很少有6D姿势估计方法使用骨干网络从RGB和深度图像中提取功能,而Uni6D是这样做的先驱。我们发现UNI6D中性能限制的主要原因是实例外部和实例 - 内噪声。 uni6d不可避免地会由于其固有的直接管道设计而从接收场中的背景像素引入实例外部噪声,并忽略了输入深度数据中的实例 - 内侧噪声。在这项工作中,我们提出了一种两步的denoising方法,以处理UNI6D中上述噪声。在第一步中,实例分割网络用于裁剪和掩盖实例,以消除非实施区域的噪声。在第二步中,提出了一个轻巧的深度剥夺模块,以校准深度特征,然后再将其输入姿势回归网络。广泛的实验表明,我们称为uni6dv2的方法能够有效,稳健地消除噪声,在不牺牲过多的推理效率的情况下超过UNI6D。它还减少了对需要昂贵标签的注释真实数据的需求。
translated by 谷歌翻译
6D object pose estimation problem has been extensively studied in the field of Computer Vision and Robotics. It has wide range of applications such as robot manipulation, augmented reality, and 3D scene understanding. With the advent of Deep Learning, many breakthroughs have been made; however, approaches continue to struggle when they encounter unseen instances, new categories, or real-world challenges such as cluttered backgrounds and occlusions. In this study, we will explore the available methods based on input modality, problem formulation, and whether it is a category-level or instance-level approach. As a part of our discussion, we will focus on how 6D object pose estimation can be used for understanding 3D scenes.
translated by 谷歌翻译
我们提出了一种方法,用于估计具有单个RGB图像的可用3D模型的刚性对象的6DOF姿势。与基于经典对应的方法不同,该方法可以预测输入图像的像素的3D对象坐标,该建议的方法可以预测3D对象坐标在相机frustum中采样的3D查询点。从像素到3D点的移动,这是受到3D重建方法的最新PIFU式方法的启发,可以对整个对象(包括(自我)遮挡部分)进行推理。对于与与像素对齐的图像功能相关的3D查询点,我们训练完全连接的神经网络来预测:(i)相应的3D对象坐标,以及(ii)签名到对象表面的签名距离,首先定义仅适用于地表附近的查询点。我们将该网络实现的映射称为神经通信字段。然后,通过Kabsch-Ransac算法从预测的3D-3D对应关系中稳健地估计对象姿势。所提出的方法在三个BOP数据集上实现了最先进的结果,并且在咬合挑战性案例中表现出了优越。项目网站在:linhuang17.github.io/ncf。
translated by 谷歌翻译
对象姿态估计有多个重要应用,例如机器人抓握和增强现实。我们提出了一种估计了提高当前提案的准确性的6D对象的6D姿势,仍然可以实时使用。我们的方法使用RGB-D数据作为段对象的输入并估计它们的姿势。它使用具有多个头部的神经网络,一个头估计对象分类并生成掩码,第二估计转换向量的值,最后一个头估计表示对象旋转的四元轴的值。这些头部利用特征提取和特征融合期间使用的金字塔架构。我们的方法可以实时使用,其低推理时间为0.12秒并具有高精度。通过这种快速推理和良好准确性的组合,可以在机器人挑选和放置任务和/或增强现实应用中使用我们的方法。
translated by 谷歌翻译
We introduce a novel method for 3D object detection and pose estimation from color images only. We first use segmentation to detect the objects of interest in 2D even in presence of partial occlusions and cluttered background. By contrast with recent patch-based methods, we rely on a "holistic" approach: We apply to the detected objects a Convolutional Neural Network (CNN) trained to predict their 3D poses in the form of 2D projections of the corners of their 3D bounding boxes. This, however, is not sufficient for handling objects from the recent T-LESS dataset: These objects exhibit an axis of rotational symmetry, and the similarity of two images of such an object under two different poses makes training the CNN challenging. We solve this problem by restricting the range of poses used for training, and by introducing a classifier to identify the range of a pose at run-time before estimating it. We also use an optional additional step that refines the predicted poses. We improve the state-of-the-art on the LINEMOD dataset from 73.7% [2] to 89.3% of correctly registered RGB frames. We are also the first to report results on the Occlusion dataset [1] using color images only. We obtain 54% of frames passing the Pose 6D criterion on average on several sequences of the T-LESS dataset, compared to the 67% of the state-of-the-art [10] on the same sequences which uses both color and depth. The full approach is also scalable, as a single network can be trained for multiple objects simultaneously.
translated by 谷歌翻译
我们提出了一个基于按键的对象级别的SLAM框架,该框架可以为对称和不对称对象提供全球一致的6DOF姿势估计。据我们所知,我们的系统是最早利用来自SLAM的相机姿势信息的系统之一,以提供先验知识,以跟踪对称对象的关键点 - 确保新测量与当前的3D场景一致。此外,我们的语义关键点网络经过训练,可以预测捕获预测的真实错误的关键点的高斯协方差,因此不仅可以作为系统优化问题中残留物的权重,而且还可以作为检测手段有害的统计异常值,而无需选择手动阈值。实验表明,我们的方法以6DOF对象姿势估算和实时速度为最先进的状态提供了竞争性能。我们的代码,预培训模型和关键点标签可用https://github.com/rpng/suo_slam。
translated by 谷歌翻译
大多数实时人类姿势估计方法都基于检测接头位置。使用检测到的关节位置,可以计算偏差和肢体的俯仰。然而,由于这种旋转轴仍然不观察,因此不能计算沿着肢体沿着肢体至关重要的曲折,这对于诸如体育分析和计算机动画至关重要。在本文中,我们引入了方向关键点,一种用于估计骨骼关节的全位置和旋转的新方法,仅使用单帧RGB图像。灵感来自Motion-Capture Systems如何使用一组点标记来估计全骨骼旋转,我们的方法使用虚拟标记来生成足够的信息,以便准确地推断使用简单的后处理。旋转预测改善了接头角度最佳报告的平均误差48%,并且在15个骨骼旋转中实现了93%的精度。该方法还通过MPJPE在原理数据集上测量,通过MPJPE测量,该方法还改善了当前的最新结果14%,并概括为野外数据集。
translated by 谷歌翻译
本文介绍了一种新型的多视图6 DOF对象姿势细化方法,重点是改进对合成数据训练的方法。它基于DPOD检测器,该检测器会在每个帧中产生密集的2D-3D对应关系。我们选择使用多个具有已知相机转换的帧,因为它允许通过可解释的ICP样损耗函数引入几何约束。损耗函数是通过可区分的渲染器实现的,并经过迭代进行了优化。我们还证明,仅根据合成数据训练的完整检测和完善管道可用于自动标记的真实数据。我们对linemod,caslusion,自制和YCB-V数据集执行定量评估,并与对合成和真实数据训练的最新方法相比,报告出色的性能。我们从经验上证明,我们的方法仅需要几个帧,并且可以在外部摄像机校准中关闭相机位置和噪音,从而使其实际用法更加容易且无处不在。
translated by 谷歌翻译
本文提出了一个统一的框架到(i)找到球,(ii)预测姿势,(iii)在团队体育场景中分段播放器的实例掩码。这些问题对自动体育分析,生产和广播有高兴趣。常见做法是通过利用通用最先进的模型,例如Panoptic-Deeblab来单独解决每个问题,用于玩家分割。除了从单任务模型的乘法乘以增加的复杂性之外,由于团队体育场景的复杂性和特异性,使用现成的架子模型也会阻碍性能,如强大的遮挡和运动模糊。为了规避这些限制,我们的论文提出培训一种单一的模型,它通过组合零件强度场和空间嵌入原理来预测球和玩家掩模和姿势。部件强度场提供球和播放器位置,以及播放器接头位置。然后利用空间嵌入来将播放器实例像素联系到其各自的播放器中心,而且还将播放器接头分组成骷髅。我们展示了拟议模型在DeepSport篮球数据集上的有效性,为单独解决每个单独任务的SOA模型实现了可比性的性能。
translated by 谷歌翻译
估计对象的6D姿势是必不可少的计算机视觉任务。但是,大多数常规方法从单个角度依赖相机数据,因此遭受遮挡。我们通过称为MV6D的新型多视图6D姿势估计方法克服了这个问题,该方法从多个角度根据RGB-D图像准确地预测了混乱场景中所有对象的6D姿势。我们将方法以PVN3D网络为基础,该网络使用单个RGB-D图像来预测目标对象的关键点。我们通过从多个视图中使用组合点云来扩展此方法,并将每个视图中的图像与密集层层融合。与当前的多视图检测网络(例如Cosypose)相反,我们的MV6D可以以端到端的方式学习多个观点的融合,并且不需要多个预测阶段或随后对预测的微调。此外,我们介绍了三个新颖的影像学数据集,这些数据集具有沉重的遮挡的混乱场景。所有这些都从多个角度包含RGB-D图像,例如语义分割和6D姿势估计。即使在摄像头不正确的情况下,MV6D也明显优于多视图6D姿势估计中最新的姿势估计。此外,我们表明我们的方法对动态相机设置具有强大的态度,并且其准确性随着越来越多的观点而逐渐增加。
translated by 谷歌翻译
实时机器人掌握,支持随后的精确反对操作任务,是高级高级自治系统的优先目标。然而,尚未找到这样一种可以用时间效率进行充分准确的掌握的算法。本文提出了一种新的方法,其具有2阶段方法,它使用深神经网络结合快速的2D对象识别,以及基于点对特征框架的随后的精确和快速的6D姿态估计来形成实时3D对象识别和抓握解决方案能够多对象类场景。所提出的解决方案有可能在实时应用上稳健地进行,需要效率和准确性。为了验证我们的方法,我们进行了广泛且彻底的实验,涉及我们自己的数据集的费力准备。实验结果表明,该方法在5CM5DEG度量标准中的精度97.37%,平均距离度量分数99.37%。实验结果显示了通过使用该方法的总体62%的相对改善(5cm5deg度量)和52.48%(平均距离度量)。此外,姿势估计执行也显示出运行时间的平均改善47.6%。最后,为了说明系统在实时操作中的整体效率,进行了一个拾取和放置的机器人实验,并显示了90%的准确度的令人信服的成功率。此实验视频可在https://sites.google.com/view/dl-ppf6dpose/上获得。
translated by 谷歌翻译
在本文中,我们考虑了同时找到和从单个2D图像中恢复多手的具有挑战性的任务。先前的研究要么关注单手重建,要么以多阶段的方式解决此问题。此外,常规的两阶段管道首先检测到手部区域,然后估计每个裁剪贴片的3D手姿势。为了减少预处理和特征提取中的计算冗余,我们提出了一条简洁但有效的单阶段管道。具体而言,我们为多手重建设计了多头自动编码器结构,每个HEAD网络分别共享相同的功能图并分别输出手动中心,姿势和纹理。此外,我们采用了一个弱监督的计划来减轻昂贵的3D现实世界数据注释的负担。为此,我们提出了一系列通过舞台训练方案优化的损失,其中根据公开可用的单手数据集生成具有2D注释的多手数据集。为了进一步提高弱监督模型的准确性,我们在单手和多个手设置中采用了几个功能一致性约束。具体而言,从本地功能估算的每只手的关键点应与全局功能预测的重新投影点一致。在包括Freihand,HO3D,Interhand 2.6M和RHD在内的公共基准测试的广泛实验表明,我们的方法在弱监督和完全监督的举止中优于基于最先进的模型方法。代码和模型可在{\ url {https://github.com/zijinxuxu/smhr}}上获得。
translated by 谷歌翻译
A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image and depth separately or use costly post-processing steps, limiting their performances in highly cluttered scenes and real-time applications. In this work, we present DenseFusion, a generic framework for estimating 6D pose of a set of known objects from RGB-D images. DenseFusion is a heterogeneous architecture that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated. Furthermore, we integrate an end-to-end iterative pose refinement procedure that further improves the pose estimation while achieving near real-time inference. Our experiments show that our method outperforms state-of-the-art approaches in two datasets, YCB-Video and LineMOD. We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose. Our code and video are available at https://sites.google.com/view/densefusion/.
translated by 谷歌翻译