Investigations on Output Parameterizations of Neural Networks for Single Shot 6D Object Pose Estimation
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所IPA）；Institute of Industrial Manufacturing and Management IFF, University of Stuttgart（斯图加特大学工业制造与管理研究所IFF）
Kilian Kleeberger, Markus Völk, Richard Bormann, Marco F. Huber
备注：
Accepted at 2021 IEEE International Conference on Robotics and Automation (ICRA 2021)
Single shot approaches have demonstrated tremendous success on various computer vision tasks. Finding good parameterizations for 6D object pose estimation remains an open challenge. In this work, we propose different novel parameterizations for the output of the neural network for single shot 6D object pose estimation. Our learning-based approach achieves state-of-the-art performance on two public benchmark datasets. Furthermore, we demonstrate that the pose estimates can be used for real-world robotic grasping tasks without additional ICP refinement.
We propose a new policy parameterization for representing 3D rotations during reinforcement learning. Today in the continuous control reinforcement learning literature, many stochastic policy parameterizations are Gaussian. We argue that universally applying a Gaussian policy parameterization is not always desirable for all environments. One such case in particular where this is true are tasks that involve predicting a 3D rotation output, either in isolation, or coupled with translation as part of a full 6D pose output. Our proposed Bingham Policy Parameterization (BPP) models the Bingham dist…
University of Toronto（多伦多大学）；Carnegie Mellon University（卡内基梅隆大学）
Real-time object pose estimation is necessary for many robot manipulation algorithms. However, state-of-the-art methods for object pose estimation are trained for a specific set of objects; these methods thus need to be retrained to estimate the pose of each new object, often requiring tens of GPU-days of training for optimal performance. In this paper, we propose the OSSID framework, leveraging a slow zero-shot pose estimator to self-supervise the training of a fast detection algorithm. This fast detector can then be used to filter the input to the pose estimator, drastically improving its in…
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural language understanding. Based on the Model-Agnostic Meta-Learning framework (MAML), we introduce the Attentive Task-Agnostic Meta-Learning (ATAML) algorithm for text classification. The essential difference between MAML and ATAML is in the separation of task-agnostic representation lear…
In this paper, we approach the task of determining sensitivity bounds for pose estimation neural networks. This task is particularly challenging as it requires characterizing the sensitivity of 3D rotations. We develop a sensitivity measure that describes the maximum rotational change in a network's output with respect to a Euclidean change in its input. We show that this measure is a type of Lipschitz constant, and that it is bounded by the product of a network's Euclidean Lipschitz constant and an intrinsic property of a rotation parameterization which we call the "distance ratio constant". …
Few-shot Learner Parameterization by Diffusion Time-steps
Nanyang Technological University（南洋理工大学）；Sea AI Lab（Sea AI实验室）；Singapore Management University（新加坡管理大学）；Hefei University of Technology（合肥工业大学）；Skywork AI
In this paper, we focus on motion estimation dedicated for non-holonomic ground robots, by probabilistically fusing measurements from the wheel odometer and exteroceptive sensors. For ground robots, the wheel odometer is widely used in pose estimation tasks, especially in applications under planar-scene based environments. However, since the wheel odometer only provides 2D motion estimates, it is extremely challenging to use that for performing accurate full 6D pose (3D position and 3D orientation) estimation. Traditional methods on 6D pose estimation either approximate sensor or motion models…
An arbitrary rigid transformation in $\mathbf{SE}(3)$ can be separated into two parts, namely, a translation and a rigid rotation. This technical report reviews, under a unifying viewpoint, three common alternatives to representing the rotation part: sets of three (yaw-pitch-roll) Euler angles, orthogonal rotation matrices from $\mathbf{SO}(3)$ and quaternions. It will be described: (i) the equivalence between these representations and the formulas for transforming one to each other (in all cases considering the translational and rotational parts as a whole), (ii) how to compose poses with pos…
Shandong University（山东大学）；City University of Hong Kong（香港城市大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）
Head pose estimation plays a vital role in various applications, e.g., driverassistance systems, human-computer interaction, virtual reality technology, and so on. We propose a novel geometry based algorithm for accurately estimating the head pose from a single 2D face image at a very low computational cost. Specifically, the rectangular coordinates of only four non-coplanar feature points from a predefined 3D facial model as well as the corresponding ones automatically/ manually extracted from a 2D face image are first normalized to exclude the effect of external factors (i.e., scale factor a…
University of Oxford（牛津大学）；Oxford Robotics Institute（牛津机器人研究所）；Visual Geometry Group（视觉几何组）
Object pose estimation is an important component of most vision pipelines for embodied agents, as well as in 3D vision more generally. In this paper we tackle the problem of estimating the pose of novel object categories in a zero-shot manner. This extends much of the existing literature by removing the need for pose-labelled datasets or category-specific CAD models for training or inference. Specifically, we make the following contributions. First, we formalise the zero-shot, category-level pose estimation problem and frame it in a way that is most applicable to real-world embodied agents. Se…
SurgPose: Generalisable Surgical Instrument Pose Estimation using Zero-Shot Learning and Stereo Vision
Department of Computing, Imperial College London（帝国理工学院计算系）；Hamlyn Centre for Robotic Surgery, Department of Surgery and Cancer, Imperial College London（帝国理工学院外科与癌症部门机器人手术中心）
Pose estimation is a basic module in many robot manipulation pipelines. Estimating the pose of objects in the environment can be useful for grasping, motion planning, or manipulation. However, current state-of-the-art methods for pose estimation either rely on large annotated training sets or simulated data. Further, the long training times for these methods prohibit quick interaction with novel objects. To address these issues, we introduce a novel method for zero-shot object pose estimation in clutter. Our approach uses a hypothesis generation and scoring framework, with a focus on learning …
Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone. This requires a remarkable degree of invariance to pose, articulation and background. A solution is to use pose-normalized representations: first localize semantic parts in each image, and then describe images by characterizing the appearance of each part. While such representations are out of favor for fully supervised classification, we show that they are extremely effective for few-shot fine-grained classification. With a mini…
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所（IPA））；University of Stuttgart（斯图加特大学）
In this paper, we introduce a novel single shot approach for 6D object pose estimation of rigid objects based on depth images. For this purpose, a fully convolutional neural network is employed, where the 3D input data is spatially discretized and pose estimation is considered as a regression task that is solved locally on the resulting volume elements. With 65 fps on a GPU, our Object Pose Network (OP-Net) is extremely fast, is optimized end-to-end, and estimates the 6D pose of multiple objects in the image simultaneously. Our approach does not require manually 6D pose-annotated real-world da…
How does one represent an action? How does one describe an action that we have never seen before? Such questions are addressed by the Zero Shot Learning paradigm, where a model is trained on only a subset of classes and is evaluated on its ability to correctly classify an example from a class it has never seen before. In this work, we present a body pose based zero shot action recognition network and demonstrate its performance on the NTU RGB-D dataset. Our model learns to jointly encapsulate visual similarities based on pose features of the action performer as well as similarities in the natu…
Hong Kong University of Science and Technology（香港科技大学）；Megvii Technology（旷视科技）
6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models. In this work, we study a new open set problem; the few-shot 6D object poses estimation: estimating the 6D pose of an unknown object by a few support views without extra training. To tackle the problem, we point out the importance of fully exploring the appearance and geometric relationship between the given support views and query scene patches and propose a dense prototypes matching framework by …
CEA LIST（法国原子能与替代能源委员会信息技术与系统实验室）；Sorbonne University（索邦大学）；CNRS（法国国家科学研究中心）；Institute for Intelligent Systems and Robotics（智能系统与机器人研究所）
In this paper, we propose a new single shot method for multi-person 3D human pose estimation in complex images. The model jointly learns to locate the human joints in the image, to estimate their 3D coordinates and to group these predictions into full human skeletons. The proposed method deals with a variable number of people and does not need bounding boxes to estimate the 3D poses. It leverages and extends the Stacked Hourglass Network and its multi-scale feature learning to manage multi-person situations. Thus, we exploit a robust 3D human pose formulation to fully describe several 3D human…
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose. End-to-end learning circumvents pose, but requires more labels to generalize. We introduce Video Pose Distillation (VPD), a weakly-supervised technique to learn features for new video domains, such as individual sports that challenge pose estimation. Under VPD, a student network learns to…
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）；Department of Computer Science, National Tsing Hua University（国立清华大学计算机科学系）；Department of Computer Science, University of Oxford（牛津大学计算机科学系）
We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction. While augmentations via interpolating feature-label pairs are effective in classification tasks, they fall short in shape predictions potentially due to inconsistencies between interpolated products of two images and volumes when rendering viewpoints are unknown. PADMix targets this issue with two sets of mixup procedures performed sequentially. We first perform an input mixup which, combined with a pose adaptive…
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 (Kehl et al., ICCV'17) 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 the …
CEA LIST（法国原子能与替代能源委员会信息与技术实验室）；Sorbonne University（索邦大学）；CNRS（法国国家科学研究中心）；Institute for Intelligent Systems and Robotics（智能系统与机器人研究所）
Recently, several deep learning models have been proposed for 3D human pose estimation. Nevertheless, most of these approaches only focus on the single-person case or estimate 3D pose of a few people at high resolution. Furthermore, many applications such as autonomous driving or crowd analysis require pose estimation of a large number of people possibly at low-resolution. In this work, we present PandaNet (Pose estimAtioN and Dectection Anchor-based Network), a new single-shot, anchor-based and multi-person 3D pose estimation approach. The proposed model performs bounding box detection and, f…
We present a novel learning framework for cloth deformation by embedding virtual cloth into a tetrahedral mesh that parametrizes the volumetric region of air surrounding the underlying body. In order to maintain this volumetric parameterization during character animation, the tetrahedral mesh is constrained to follow the body surface as it deforms. We embed the cloth mesh vertices into this parameterization of three-dimensional space in order to automatically capture much of the nonlinear deformation due to both joint rotations and collisions. We then train a convolutional neural network to re…
Zero-shot High-fidelity and Pose-controllable Character Animation
Fudan University（复旦大学）；Shanghai Key Lab of Intell. Info. Processing（上海智能信息处理重点实验室）；School of CS, Fudan University（复旦大学计算机科学技术学院）；Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）；OPPO AI Center（OPPO人工智能中心）；South China University Of Technology（华南理工大学）；Westlake University（西湖大学）
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China 2 School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China（1 中国科学院信息工程研究所，北京，中国 2 中国科学院大学网络空间安全学院，北京，中国）
One-shot talking head generation produces lip-sync talking heads based on arbitrary audio and one source face. To guarantee the naturalness and realness, recent methods propose to achieve free pose control instead of simply editing mouth areas. However, existing methods do not preserve accurate identity of source face when generating head motions. To solve the identity mismatch problem and achieve high-quality free pose control, we present One-shot Pose-controllable Talking head generation network (OPT). Specifically, the Audio Feature Disentanglement Module separates content features from aud…
University of Texas at Dallas（德克萨斯大学达拉斯分校）；NVIDIA（英伟达）
We introduce the Few-Shot Object Learning (FewSOL) dataset for object recognition with a few images per object. We captured 336 real-world objects with 9 RGB-D images per object from different views. Object segmentation masks, object poses and object attributes are provided. In addition, synthetic images generated using 330 3D object models are used to augment the dataset. We investigated (i) few-shot object classification and (ii) joint object segmentation and few-shot classification with the state-of-the-art methods for few-shot learning and meta-learning using our dataset. The evaluation re…
For applications in navigation and robotics, estimating the 3D pose of objects is as important as detection. Many approaches to pose estimation rely on detecting or tracking parts or keypoints [11, 21]. In this paper we build on a recent state-of-the-art convolutional network for slidingwindow detection [10] to provide detection and rough pose estimation in a single shot, without intermediate stages of detecting parts or initial bounding boxes. While not the first system to treat pose estimation as a categorization problem, this is the first attempt to combine detection and pose estimation at …
Zhejiang University（浙江大学）；The University of Sydney（悉尼大学）；Image Derivative Inc.（图像衍生公司）
We propose a new method for object pose estimation without CAD models. The previous feature-matching-based method OnePose has shown promising results under a one-shot setting which eliminates the need for CAD models or object-specific training. However, OnePose relies on detecting repeatable image keypoints and is thus prone to failure on low-textured objects. We propose a keypoint-free pose estimation pipeline to remove the need for repeatable keypoint detection. Built upon the detector-free feature matching method LoFTR, we devise a new keypoint-free SfM method to reconstruct a semi-dense po…
We present a novel one-shot method for object detection and 6 DoF pose estimation, that does not require training on target objects. At test time, it takes as input a target image and a textured 3D query model. The core idea is to represent a 3D model with a number of 2D templates rendered from different viewpoints. This enables CNN-based direct dense feature extraction and matching. The object is first localized in 2D, then its approximate viewpoint is estimated, followed by dense 2D-3D correspondence prediction. The final pose is computed with PnP. We evaluate the method on LineMOD, Occlusio…
Universal Features Guided Zero-Shot Category-Level Object Pose Estimation
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Hong Kong University of Science and Technology（香港科技大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）
Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view. Addressing this ambiguity requires to aggregate various cues over the entire image, such as body sizes, scene layouts, and inter-person relationships. However, most previous methods adopt a top-down scheme that first performs 2D pose detection and then regresses the 3D pose and scale for each detected person individually, ignoring global contextual cues. In this paper, we propose a novel system that first regresses a set of 2.5…
