Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, current methods rely on shape priors or CAD models of the intra-class known objects. We propose a diffusion-based monocular category-level 9D object pose generation method, MonoDiff9D. Our motivation is to leverage the probabilistic nature of diffusion models to alleviate the need for shape priors, CAD models, or depth sensors for intra-class unknown object pose estimation. We first estimate coarse depth via DINOv2 from the monocular image in a zero-shot manner and convert it into a point cloud. We then fuse the global features of the point cloud with the input image and use the fused features along with the encoded time step to condition MonoDiff9D. Finally, we design a transformer-based denoiser to recover the object pose from Gaussian noise. Extensive experiments on two popular benchmark datasets show that MonoDiff9D achieves state-of-the-art monocular category-level 9D object pose estimation accuracy without the need for shape priors or CAD models at any stage. Our code will be made public at https://github.com/CNJianLiu/MonoDiff9D.

The location accuracy of fixed anchors plays a pivotal role in ultrawideband (UWB) positioning. However, existing calibration methods for calculating the anchor positions require anchor-to-anchor communication or known initial values for anchor locations. Moreover, the calibration accuracy is adversely affected by non line-of-sight (NLOS) conditions. We propose a two-stage calibration scheme to conduct simultaneous calibration and localization (SCAL) based on UWB-inertial measurement unit (IMU)–odometer sensor fusion without the need for anchor-to-anchor communication or manual intervention. Our method performs IMU-odometer-aided multidimensional scaling (IO-MDS) to provide the initial calibration value without anchor-to-anchor ranging measurements. This is followed by a novel factor-graph-based framework to achieve coarse-to-fine calibration based on UWB, inertial, and odometer measurements. In existing works, a single UWB range measurement is regarded as a weak constraint, as it often leads to incorrect estimates. Our method uses the derived radial velocity (DRV) and IO-MDS factors as additional strong constraints for reliable estimates. To minimize the NLOS influence on the calibration process, we introduce an improved least square-support vector machine (ILS-SVM) based on adaptive weight parameter and multikernel function. Experimental results on two field collected datasets show enhancements in NLOS identification and SCAL. In the lab dataset, identification accuracy increased by 5.5%, with improvements of 0.124 m and 0.309 m in root mean square error (RMSE) for robot and anchor locations, respectively. In the parking lot dataset, identification accuracy improved by 5.0%, with RMSE improvements of 0.223 m and 0.317 m for robot and anchor locations, respectively.

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance.

Visual understanding of 3-D objects is essential for robotic manipulation, autonomous navigation, and augmented reality. However, existing methods struggle to perform this task efficiently and accurately in an end-to-end manner. We propose a single-shot method based on the state space model (SSM) to predict the full 3-D information (pose, size, shape) of multiple 3-D objects from a single RGB-D image in an end-to-end manner. Our method first encodes long-range semantic information from RGB and depth images separately and then combines them into an integrated latent representation that is processed by a modified SSM to infer the full 3-D information in two separate task heads within a unified model. A heatmap/detection head predicts object centers, and a 3-D information head predicts a matrix detailing the pose, size and latent code of shape for each detected object. We also propose a shape autoencoder based on the SSM, which learns canonical shape codes derived from a large database of 3-D point cloud shapes. The end-to-end framework, modified SSM block and SSM-based shape autoencoder form major contributions of this work. Our design includes different scan strategies tailored to different input data representations, such as RGB-D images and point clouds. Extensive evaluations on the REAL275, CAMERA25, and Wild6D datasets show that our method achieves state-of-the-art performance. On the large-scale Wild6D dataset, our model significantly outperforms the nearest competitor, achieving 2.6% and 5.1% improvements on the IOU-50 and 5°10 cm metrics, respectively.

Six-degree-of-freedom (6DoF) object pose estimation is a crucial task for virtual reality and accurate robotic manipulation. Category-level 6DoF pose estimation has recently become popular as it improves generalization to a complete category of objects. However, current methods focus on data-driven differential learning, which makes them highly dependent on the quality of the real-world labeled data and limits their ability to generalize to unseen objects. To address this problem, we propose multi-hypothesis (MH) consistency learning (MH6D) for category-level 6-D object pose estimation without using real-world training data. MH6D uses a parallel consistency learning structure, alleviating the uncertainty problem of single-shot feature extraction and promoting self-adaptation of domain to reduce the synthetic-to-real domain gap. Specifically, three randomly sampled pose transformations are first performed in parallel on the input point cloud. An attention-guided category-level 6-D pose estimation network with channel attention (CA) and global feature cross-attention (GFCA) modules is then proposed to estimate the three hypothesized 6-D object poses by extracting and fusing the global and local features effectively. Finally, we propose a novel loss function that considers both the process and the final result information allowing MH6D to perform robust consistency learning. We conduct experiments under two different training data settings (i.e., only synthetic data and synthetic and real-world data) to verify the generalization ability of MH6D. Extensive experiments on benchmark datasets demonstrate that MH6D achieves state-of-the-art (SOTA) performance, outperforming most data-driven methods even without using any real-world data. The code is available at https://github.com/CNJianLiu/MH6D.

Vision-guided robotic picking in 3-D space is a key technology for industrial automation and intelligent manufacturing. However, existing methods rely on labeled real-world data for learning, significantly limiting their ability to generalize to novel objects and robustness to challenging scenes containing occlusions and clutter. To address these problems, we propose a domain-generalized robotic picking method (DGPF6D) that builds on contrastive learning-based 6-D pose estimation. DGPF6D generalizes to real-world scenes by training only on synthetic data and without using shape priors. Specifically, we first perform continuous data augmentations on the synthetic RGB and point cloud images such that they can better simulate real-world scenes with occlusions and clutter. We then feed the augmented images in parallel to a two-stage (i.e., 3-D shape reconstruction and 6-D pose estimation) contrastive learning framework, thereby enhancing the domain-generalization ability and robustness of DGPF6D. Moreover, we propose a point cloud cross attention-guided intracategory unknown object 3-D shape reconstruction network, which can effectively fuse the observed and the unit random point clouds and explicitly highlight their differences, thus avoiding the dependence of DGPF6D on shape priors. Finally, we build a robotic picking system employing DGPF6D to realize domain-generalized robotic picking in 3-D space. Extensive experiments on two benchmarks and real-world scenes show that DGPF6D achieves state-of-the-art performance, and can be effectively applied for domain-generalized robotic picking.

The rise of the Internet of Things has spurred the growth of wireless applications, particularly Wi-Fi-based indoor localization, which is gaining prominence owing to its cost-effectiveness. Nevertheless, the accuracy of Wi-Fi-based indoor localization is hindered by signal instability. To address this limitation, we introduce an interval random analysis approach for uncertain Wi-Fi-based indoor localization. Specifically, this approach employs an interval random parameter lognormal shadowing model for radio map enhancement and adaptive Bayesian comprehensive learning (IRPLS-ABCL) particle swarm optimization (PSO) for location estimation accuracy enhancement. The process comprises two stages: offline training and online localization. During the offline phase, we establish the interval random parameter lognormal shadowing model, considering the parameters as interval random variables, rather than precise values, in a sparse reference point scenario. In the online phase, we use a double-panel fingerprint homogeneity model to assess fingerprint similarity and apply the adaptive Bayesian comprehensive learning PSO algorithm to enhance localization precision. The experimental results show that the proposed algorithm can achieve the best performance in terms of localization accuracy based on the predicted average received signal strength (RSS), reaching 1.89 m.

Robotic grasping is one of the key functions for realizing industrial automation and human–machine interaction. However, current robotic grasping methods for unknown objects mainly focus on generating the 6-D grasp poses, which cannot obtain rich object pose information and are not robust in challenging scenes. Based on this, in this article, we propose a robotic continuous grasping system that achieves end-to-end robotic grasping of intraclass unknown objects in 3-D space by accurate category-level 6-D object pose estimation. Specifically, to achieve object pose estimation, first, we propose a global shape extraction network (GSENet) based on ResNet1D to extract the global shape of an object category from the 3-D models of intraclass known objects. Then, with the global shape as the prior feature, we propose a transformer-guided network to reconstruct the shape of intraclass unknown object. The proposed network can effectively introduce internal and mutual communication between the prior feature, current feature, and their difference feature. The internal communication is performed by self-attention. The mutual communication is performed by cross attention to strengthen their correlation. To achieve robotic grasping for multiple objects, we propose a low-computation and effective grasping strategy based on the predefined vector orientation, and develop a graphical user interface for monitoring and control. Experiments on two benchmark datasets demonstrate that our system achieves state-of-the-art 6-D pose estimation accuracy. Moreover, the real-world experiments show that our system also achieves superior robotic grasping performance, with a grasping success rate of 81.6$\%$for multiple objects.

Tracking the 6-degree-of-freedom (6D) object pose in video sequences is gaining attention because it has a wide application in multimedia and robotic manipulation. However, current methods often perform poorly in challenging scenes, such as incorrect initial pose, sudden re-orientation, and severe occlusion. In contrast, we present a robust 6D object pose tracking method with a novel hierarchical feature fusion network, refer it as HFF6D, which aims to predict the object’s relative pose between adjacent frames. Instead of extracting features from adjacent frames separately, HFF6D establishes sufficient spatial-temporal information interaction between adjacent frames. In addition, we propose a novel subtraction feature fusion (SFF) module with attention mechanism to leverage feature subtraction during feature fusion. It explicitly highlights the feature differences between adjacent frames, thus improving the robustness of relative pose estimation in challenging scenes. Besides, we leverage data augmentation technology to make HFF6D be used more effectively in the real world by training only with synthetic data, thereby reducing manual effort in data annotation. We evaluate HFF6D on the well-known YCB-Video and YCBInEOAT datasets. Quantitative and qualitative results demonstrate that HFF6D outperforms state-of-the-art (SOTA) methods in both accuracy and efficiency. Moreover, it is also proved to achieve high-robustness tracking under the above-mentioned challenging scenes.

Deep learning models achieve impressive performance for skeleton-based human action recognition. Graph convolutional networks (GCNs) are particularly suitable for this task due to the graph-structured nature of skeleton data. However, the robustness of these models to adversarial attacks remains largely unexplored due to their complex spatiotemporal nature that must represent sparse and discrete skeleton joints. This work presents the first adversarial attack on skeleton-based action recognition with GCNs. The proposed targeted attack, termed constrained iterative attack for skeleton actions (CIASA), perturbs joint locations in an action sequence such that the resulting adversarial sequence preserves the temporal coherence, spatial integrity, and the anthropomorphic plausibility of the skeletons. CIASA achieves this feat by satisfying multiple physical constraints and employing spatial skeleton realignments for the perturbed skeletons along with regularization of the adversarial skeletons with generative networks. We also explore the possibility of semantically imperceptible localized attacks with CIASA and succeed in fooling the state-of-the-art skeleton action recognition models with high confidence. CIASA perturbations show high transferability in black-box settings. We also show that the perturbed skeleton sequences are able to induce adversarial behavior in the RGB videos created with computer graphics. A comprehensive evaluation with NTU and Kinetics data sets ascertains the effectiveness of CIASA for graph-based skeleton action recognition and reveals the imminent threat to the spatiotemporal deep learning tasks in general.

Recent advances in Deep Learning show the existence of image-agnostic quasi-imperceptible perturbations that when applied to 'any' image can fool a state-of-the-art network classifier to change its prediction about the image label. These 'Universal Adversarial Perturbations' pose a serious threat to the success of Deep Learning in practice. We present the first dedicated framework to effectively defend the networks against such perturbations. Our approach learns a Perturbation Rectifying Network (PRN) as 'pre-input' layers to a targeted model, such that the targeted model needs no modification. The PRN is learned from real and synthetic image-agnostic perturbations, where an efficient method to compute the latter is also proposed. A perturbation detector is separately trained on the Discrete Cosine Transform of the input-output difference of the PRN. A query image is first passed through the PRN and verified by the detector. If a perturbation is detected, the output of the PRN is used for label prediction instead of the actual image. A rigorous evaluation shows that our framework can defend the network classifiers against unseen adversarial perturbations in the real-world scenarios with up to 97.5% success rate. The PRN also generalizes well in the sense that training for one targeted network defends another network with a comparable success rate.

Convolutional Neural Networks (CNN) have performed extremely well for many image analysis tasks. However, supervised training of deep CNN architectures requires huge amounts of labelled data which is unavailable for light field images. In this paper, we leverage on synthetic light field images and propose a two stream CNN network that learns to estimate the disparities of multiple correlated neighbourhood pixels from their Epipolar Plane Images (EPI). Since the EPIs are unrelated except at their intersection, a two stream network is proposed to learn convolution weights individually for the EPIs and then combine the outputs of the two streams for disparity estimation. The CNN estimated disparity map is then refined using the central RGB light field image as a prior in a variational technique. We also propose a new real world dataset comprising light field images of 19 objects captured with the Lytro Illum camera in outdoor scenes and their corresponding 3D pointclouds, as ground truth, captured with the 3dMD scanner. This dataset will be made public to allow more precise 3D pointcloud level comparison of algorithms in the future which is currently not possible. Experiments on the synthetic and real world datasets show that our algorithm outperforms existing state-of-the-art for depth estimation from light field images.