We propose a technique for learning single-view 3D object pose estimation models by utilizing a new source of data -- in-the-wild videos where objects turn. Such videos are prevalent in practice (e.g., cars in roundabouts, airplanes near runways) and easy to collect. We show that classical structure-from-motion algorithms, coupled with the recent advances in instance detection and feature matching, provides surprisingly accurate relative 3D pose estimation on such videos. We propose a multi-stage training scheme that first learns a canonical pose across a collection of videos and then supervises a model for single-view pose estimation. The proposed technique achieves competitive performance with respect to existing state-of-the-art on standard benchmarks for 3D pose estimation, without requiring any pose labels during training. We also contribute an Accidental Turntables Dataset, containing a challenging set of 41,212 images of cars in cluttered backgrounds, motion blur and illumination changes that serves as a benchmark for 3D pose estimation.

Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. In this paper, we address the problem of unsupervised viewpoint estimation. We formulate this as a self-supervised learning task, where image reconstruction provides the supervision needed to predict the camera viewpoint. Specifically, we make use of pairs of images of the same object at training time, from unknown viewpoints, to self-supervise training by combining the viewpoint information from one image with the appearance information from the other. We demonstrate that using a perspective spatial transformer allows efficient viewpoint learning, outperforming existing unsupervised approaches on synthetic data, and obtains competitive results on the challenging PASCAL3D+ dataset.

We introduce an approach for recovering the 6D pose of multiple known objects in a scene captured by a set of input images with unknown camera viewpoints. First, we present a single-view single-object 6D pose estimation method, which we use to generate 6D object pose hypotheses. Second, we develop a robust method for matching individual 6D object pose hypotheses across different input images in order to jointly estimate camera viewpoints and 6D poses of all objects in a single consistent scene. Our approach explicitly handles object symmetries, does not require depth measurements, is robust to missing or incorrect object hypotheses, and automatically recovers the number of objects in the scene. Third, we develop a method for global scene refinement given multiple object hypotheses and their correspondences across views. This is achieved by solving an object-level bundle adjustment problem that refines the poses of cameras and objects to minimize the reprojection error in all views. We demonstrate that the proposed method, dubbed Cosy-Pose, outperforms current state-of-the-art results for single-view and multi-view 6D object pose estimation by a large margin on two challenging benchmarks: the YCB-Video and T-LESS datasets. Code and pre-trained models are available on the project webpage. 5

We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training. While NeRF is usually trained with ground-truth camera poses, multiple extensions have been proposed to reduce the need for this expensive supervision. Nonetheless, most of these methods still struggle in complex settings with large camera movements, and are restricted to single scenes, i.e. they cannot be trained on a collection of scenes depicting the same object category. To address these issues, our method uses an analysis by synthesis approach, combining a conditional NeRF with a viewpoint predictor and a scene encoder in order to produce self-supervised reconstructions for whole object categories. Rather than focusing on high fidelity reconstruction, we target efficient and accurate viewpoint prediction in complex scenarios, e.g. 360{\deg} rotation on real data. Our model shows competitive results on synthetic and real datasets, both for single scenes and multi-instance collections.

学习3D对象类别的传统方法使用合成数据或手动监控。在本文中，我们提出了一种不需要手动注释的方法，而是通过观察来自移动的有利点的物体来阐述。我们的系统在两种创新上构建：暹罗视点分解网络，不太明确地比较3D形状，强大地对准不同的视频;和3D形状完成网络可以从部分观察中提取对象的完整形状。我们还展示了配置网络来执行概率预测以及几何感知数据增强方案的好处。我们在公开可用的基准上获得最先进的结果。

现代计算机视觉已超越了互联网照片集的领域，并进入了物理世界，通过非结构化的环境引导配备摄像头的机器人和自动驾驶汽车。为了使这些体现的代理与现实世界对象相互作用，相机越来越多地用作深度传感器，重建了各种下游推理任务的环境。机器学习辅助的深度感知或深度估计会预测图像中每个像素的距离。尽管已经在深入估算中取得了令人印象深刻的进步，但仍然存在重大挑战：（1）地面真相深度标签很难大规模收集，（2）通常认为相机信息是已知的，但通常是不可靠的，并且（3）限制性摄像机假设很常见，即使在实践中使用了各种各样的相机类型和镜头。在本论文中，我们专注于放松这些假设，并描述将相机变成真正通用深度传感器的最终目标的贡献。

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we propose a set of improvements, which together result in both quantitatively and qualitatively improved depth maps compared to competing self-supervised methods.Research on self-supervised monocular training usually explores increasingly complex architectures, loss functions, and image formation models, all of which have recently helped to close the gap with fully-supervised methods. We show that a surprisingly simple model, and associated design choices, lead to superior predictions. In particular, we propose (i) a minimum reprojection loss, designed to robustly handle occlusions, (ii) a full-resolution multi-scale sampling method that reduces visual artifacts, and (iii) an auto-masking loss to ignore training pixels that violate camera motion assumptions. We demonstrate the effectiveness of each component in isolation, and show high quality, state-of-the-art results on the KITTI benchmark.

我们介绍了TemPCLR，这是一种针对3D手重建的结构化回归任务的新的时代对比学习方法。与以前的手部姿势估计方法相抵触方法不同，我们的框架考虑了其增强方案中的时间一致性，并说明了沿时间方向的手部姿势的差异。我们的数据驱动方法利用了未标记的视频和标准CNN，而无需依赖合成数据，伪标签或专业体系结构。我们的方法在HO-3D和Freihand数据集中分别将全面监督的手部重建方法的性能提高了15.9％和7.6％，从而确立了新的最先进的性能。最后，我们证明了我们的方法会随着时间的推移产生更平滑的手部重建，并且与以前的最新作品相比，对重型的闭塞更为强大，我们在定量和定性上表现出来。我们的代码和模型将在https://eth-ait.github.io/tempclr上找到。

6D对象姿势估计是计算机视觉和机器人研究中的基本问题之一。尽管最近在同一类别内将姿势估计概括为新的对象实例（即类别级别的6D姿势估计）方面已做出了许多努力，但考虑到有限的带注释数据，它仍然在受限的环境中受到限制。在本文中，我们收集了Wild6D，这是一种具有不同实例和背景的新的未标记的RGBD对象视频数据集。我们利用这些数据在野外概括了类别级别的6D对象姿势效果，并通过半监督学习。我们提出了一个新模型，称为呈现姿势估计网络reponet，该模型使用带有合成数据的自由地面真实性共同训练，以及在现实世界数据上具有轮廓匹配的目标函数。在不使用实际数据上的任何3D注释的情况下，我们的方法优于先前数据集上的最先进方法，而我们的WILD6D测试集（带有手动注释进行评估）则优于较大的边距。带有WILD6D数据的项目页面：https：//oasisyang.github.io/semi-pose。

鉴于其经济性与多传感器设置相比，从单眼输入中感知的3D对象对于机器人系统至关重要。它非常困难，因为单个图像无法提供预测绝对深度值的任何线索。通过双眼方法进行3D对象检测，我们利用了相机自我运动提供的强几何结构来进行准确的对象深度估计和检测。我们首先对此一般的两视案例进行了理论分析，并注意两个挑战：1）来自多个估计的累积错误，这些估计使直接预测棘手； 2）由静态摄像机和歧义匹配引起的固有难题。因此，我们建立了具有几何感知成本量的立体声对应关系，作为深度估计的替代方案，并以单眼理解进一步补偿了它，以解决第二个问题。我们的框架（DFM）命名为深度（DFM），然后使用已建立的几何形状将2D图像特征提升到3D空间并检测到其3D对象。我们还提出了一个无姿势的DFM，以使其在摄像头不可用时可用。我们的框架在Kitti基准测试上的优于最先进的方法。详细的定量和定性分析也验证了我们的理论结论。该代码将在https://github.com/tai-wang/depth-from-motion上发布。

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.

We introduce MegaPose, a method to estimate the 6D pose of novel objects, that is, objects unseen during training. At inference time, the method only assumes knowledge of (i) a region of interest displaying the object in the image and (ii) a CAD model of the observed object. The contributions of this work are threefold. First, we present a 6D pose refiner based on a render&compare strategy which can be applied to novel objects. The shape and coordinate system of the novel object are provided as inputs to the network by rendering multiple synthetic views of the object's CAD model. Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner. Third, we introduce a large-scale synthetic dataset of photorealistic images of thousands of objects with diverse visual and shape properties and show that this diversity is crucial to obtain good generalization performance on novel objects. We train our approach on this large synthetic dataset and apply it without retraining to hundreds of novel objects in real images from several pose estimation benchmarks. Our approach achieves state-of-the-art performance on the ModelNet and YCB-Video datasets. An extensive evaluation on the 7 core datasets of the BOP challenge demonstrates that our approach achieves performance competitive with existing approaches that require access to the target objects during training. Code, dataset and trained models are available on the project page: https://megapose6d.github.io/.

为了获取3D注释，我们仅限于受控环境或合成数据集，导致我们到3D数据集，其概括为现实世界方案。为了在半监督3D手形状和姿势估计的上下文中解决这个问题，我们提出了姿势对齐网络，以将标记帧传播到附近的稀疏注释视频中的附近未标记帧的3D注释。我们表明，在标记 - 未标记的帧对对对准监控允许我们提高姿态估计精度。此外，我们表明所提出的姿势对齐网络可以有效地传播在不良稀疏的视频上的注释而无需微调。

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation. Specifically, we use unsupervised motion-based segmentation on videos to obtain segments, which we use as 'pseudo ground truth' to train a convolutional network to segment objects from a single frame. Given the extensive evidence that motion plays a key role in the development of the human visual system, we hope that this straightforward approach to unsupervised learning will be more effective than cleverly designed 'pretext' tasks studied in the literature. Indeed, our extensive experiments show that this is the case. When used for transfer learning on object detection, our representation significantly outperforms previous unsupervised approaches across multiple settings, especially when training data for the target task is scarce.

在本文中，我们介绍一种方法来自动重建与来自单个RGB视频相互作用的人的3D运动。我们的方法估计人的3D与物体姿势，接触位置和施加在人体上的接触力的姿势。这项工作的主要贡献是三倍。首先，我们介绍一种通过建模触点和相互作用的动态来联合估计人与人的运动和致动力的方法。这是一个大规模的轨迹优化问题。其次，我们开发一种方法来从输入视频自动识别，从输入视频中识别人和物体或地面之间的2D位置和时序，从而显着简化了优化的复杂性。第三，我们在最近的视频+ Mocap数据集上验证了捕获典型的Parkour行动的方法，并在互联网视频的新数据集上展示其表现，显示人们在不受约束的环境中操纵各种工具。

第一人称视频在其持续环境的背景下突出了摄影师的活动。但是，当前的视频理解方法是从短视频剪辑中的视觉特征的原因，这些视频片段与基础物理空间分离，只捕获直接看到的东西。我们提出了一种方法，该方法通过学习摄影师（潜在看不见的）本地环境来促进以人为中心的环境的了解来链接以自我为中心的视频和摄像机随着时间的推移而张开。我们使用来自模拟的3D环境中的代理商的视频进行训练，在该环境中，环境完全可以观察到，并在看不见的环境的房屋旅行的真实视频中对其进行测试。我们表明，通过将视频接地在其物理环境中，我们的模型超过了传统的场景分类模型，可以预测摄影师所处的哪个房间（其中帧级信息不足），并且可以利用这种基础来定位与环境相对应的视频瞬间 - 中心查询，优于先验方法。项目页面：http：//vision.cs.utexas.edu/projects/ego-scene-context/

人类对象与铰接物体的相互作用在日常生活中很普遍。尽管单视图3D重建方面取得了很多进展，但从RGB视频中推断出一个铰接的3D对象模型仍然具有挑战性，显示一个人操纵对象的人。我们从RGB视频中划定了铰接的3D人体对象相互作用重建的任务，并对这项任务进行了五个方法家族的系统基准：3D平面估计，3D Cuboid估计，CAD模型拟合，隐式现场拟合以及自由 - 自由 - 形式网状配件。我们的实验表明，即使提供了有关观察到的对象的地面真相信息，所有方法也难以获得高精度结果。我们确定使任务具有挑战性的关键因素，并为这项具有挑战性的3D计算机视觉任务提出指示。短视频摘要https://www.youtube.com/watch?v=5talkbojzwc

从2D图像中学习可变形的3D对象通常是一个不适的问题。现有方法依赖于明确的监督来建立多视图对应关系，例如模板形状模型和关键点注释，这将其在“野外”中的对象上限制了。建立对应关系的一种更自然的方法是观看四处移动的对象的视频。在本文中，我们介绍了Dove，一种方法，可以从在线可用的单眼视频中学习纹理的3D模型，而无需关键点，视点或模板形状监督。通过解决对称性诱导的姿势歧义并利用视频中的时间对应关系，该模型会自动学会从每个单独的RGB框架中分解3D形状，表达姿势和纹理，并准备在测试时间进行单像推断。在实验中，我们表明现有方法无法学习明智的3D形状，而无需其他关键点或模板监督，而我们的方法在时间上产生了时间一致的3D模型，可以从任意角度来对其进行动画和呈现。

在全球坐标系中，基于颜色的双手3D姿势估计在许多应用中至关重要。但是，很少有专门用于此任务的数据集，并且没有现有数据集支持在非实验室环境中的估计。这在很大程度上归因于3D手姿势注释所需的复杂数据收集过程，这也导致难以获得野生估计所需的视觉多样性水平的实例。为了实现这一目标，最近提出了一个大规模的数据集EGO2HANDS来解决野外双手分割和检测的任务。拟议的基于组成的数据生成技术可以创建具有质量，数量和多样性的双手实例，从而将其推广到看不见的域。在这项工作中，我们提出了EGO2Handspose，这是包含3D手姿势注释的EGO2HAND的扩展，并且是第一个在看不见域中启用基于颜色的两手3D跟踪的数据集。为此，我们开发了一组参数拟合算法以启用1）使用单个图像的3D手姿势注释，2）自动转换从2D到3D手势和3）具有时间一致性的准确双手跟踪。我们在多阶段管道上提供了增量的定量分析，并表明我们数据集中的培训达到了最新的结果，这些结果大大胜过其他数据集，以实现以自我为中心的双手全球3D姿势估计的任务。

人类可以轻松地在不知道它们的情况下段移动移动物体。从持续的视觉观测中可能出现这种对象，激励我们与未标记的视频同时进行建模和移动。我们的前提是视频具有通过移动组件相关的相同场景的不同视图，并且右区域分割和区域流程将允许相互视图合成，其可以从数据本身检查，而无需任何外部监督。我们的模型以两个单独的路径开头：一种外观途径，其输出单个图像的基于特征的区域分割，以及输出一对图像的运动功能的运动路径。然后，它将它们绑定在称为段流的联合表示中，该分段流汇集在每个区域上的流程偏移，并提供整个场景的移动区域的总表征。通过培训模型，以最小化基于段流的视图综合误差，我们的外观和运动路径自动学习区域分割和流量估计，而不分别从低级边缘或光学流量构建它们。我们的模型展示了外观途径中对象的令人惊讶的出现，超越了从图像的零射对对象分割上的工作，从带有无监督的测试时间适应的视频移动对象分割，并通过监督微调，通过监督微调。我们的工作是来自视频的第一个真正的零点零点对象分段。它不仅开发了分割和跟踪的通用对象，而且还优于无增强工程的基于普遍的图像对比学习方法。