刚性物体的6D位姿估计是计算机视觉中一项长期存在且具有挑战性的任务。近年来，深度学习的兴起展现了卷积神经网络（CNNs）预测可靠6D位姿的潜力。鉴于直接位姿回归网络目前表现出次优性能，大多数方法仍在不同程度上依赖传统技术。例如，性能顶尖的方法通常采用间接策略：首先建立2D-3D或3D-3D对应关系，随后应用基于RANSAC的PnP或Kabsch算法，还会进一步使用ICP进行优化。尽管性能有所提升，但传统技术的集成使得网络耗时较长且无法端到端训练。与这些方法不同，本文提出了一种全学习式的物体位姿估计器。在这项工作中，我们首先对直接和间接方法进行了深入研究，提出了一种简单而有效的几何引导直接回归网络（GDRN），以端到端的方式从单目图像中学习6D位姿。随后，我们引入了一个几何引导的位姿优化模块，在有额外深度数据可用时提升位姿精度。在预测的坐标图引导下，我们构建了一个端到端可微的架构，该架构在观测到的RGB-D图像与渲染的RGB-D图像之间建立鲁棒且准确的3D-3D对应关系，以优化位姿。我们增强后的位姿估计流水线GDRNPP（GDRN Plus Plus）连续两年登顶BOP挑战赛排行榜，成为首个在精度和速度上均超越所有依赖传统技术的现有方法的方案。代码和模型可在https://github.com/shanice-l/gdrnpp_bop2022 获取。
英文摘要：
6D pose estimation of rigid objects is a long-standing and challenging task in computer vision. Recently, the emergence of deep learning reveals the potential of Convolutional Neural Networks (CNNs) to predict reliable 6D poses. Given that direct pose regression networks currently exhibit suboptimal performance, most methods still resort to traditional techniques to varying degrees. For example, top-performing methods often adopt an indirect strategy by first establishing 2D-3D or 3D-3D correspondences followed by applying the RANSAC-based PnP or Kabsch algorithms, and further employing ICP for refinement. Despite the performance enhancement, the integration of traditional techniques makes the networks time-consuming and not end-to-end trainable. Orthogonal to them, this paper introduces a fully learning-based object pose estimator. In this work, we first perform an in-depth investigation of both direct and indirect methods and propose a simple yet effective Geometry-guided Direct Regression Network (GDRN) to learn the 6D pose from monocular images in an end-to-end manner. Afterwards, we introduce a geometry-guided pose refinement module, enhancing pose accuracy when extra depth data is available. Guided by the predicted coordinate map, we build an end-to-end differentiable architecture that establishes robust and accurate 3D-3D correspondences between the observed and rendered RGB-D images to refine the pose. Our enhanced pose estimation pipeline GDRNPP (GDRN Plus Plus) conquered the leaderboard of the BOP Challenge for two consecutive years, becoming the first to surpass all prior methods that relied on traditional techniques in both accuracy and speed. The code and models are available at https://github.com/shanice-l/gdrnpp_bop2022.
In this paper, we tackle the problem of active robotic 3D reconstruction of an object. In particular, we study how a mobile robot with an arm-held camera can select a favorable number of views to recover an object's 3D shape efficiently. Contrary to the existing solution to this problem, we leverage the popular neural radiance fields-based object representation, which has recently shown impressive results for various computer vision tasks. However, it is not straightforward to directly reason about an object's explicit 3D geometric details using such a representation, making the next-best-view…
With increasing applications of 3D hand pose estimation in various human-computer interaction applications, convolution neural networks (CNNs) based estimation models have been actively explored. However, the existing models require complex architectures or redundant computational resources to trade with the acceptable accuracy. To tackle this limitation, this paper proposes HandFoldingNet, an accurate and efficient hand pose estimator that regresses the hand joint locations from the normalized 3D hand point cloud input. The proposed model utilizes a folding-based decoder that folds a given 2D…
TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Agricultural Information Institute, Chinese Academy of Agricultural Sciences（中国农业科学院农业信息研究所）
PCA Lab, Nanjing University of Science and Technology（南京理工大学PCA实验室）
In this paper, by modeling the point cloud registration task as a Markov decision process, we propose an end-to-end deep model embedded with the cross-entropy method (CEM) for unsupervised 3D registration. Our model consists of a sampling network module and a differentiable CEM module. In our sampling network module, given a pair of point clouds, the sampling network learns a prior sampling distribution over the transformation space. The learned sampling distribution can be used as a "good" initialization of the differentiable CEM module. In our differentiable CEM module, we first propose a ma…
TextSplat: Text-Guided Semantic Fusion for Generalizable Gaussian Splatting
Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究所）；Guangdong Laboratory of Artificial Intelligence（广东省人工智能与数字经济实验室）；Peking University（北京大学）；School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；Hangzhou Dianzi University（杭州电子科技大学）；Central Laboratory of Lishui Hospital of Wenzhou Medical University, The First Affiliated Hospital of Lishui University, Lishui People's Hospital（丽水市人民医院中央实验室、丽水大学第一附属医院、丽水人民医院）
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Zhengzhou University（郑州大学）；University of Wollongong（伍伦贡大学）
Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images. They are either not accurate, time-consuming in training or error accumulative. In this paper, we propose a method consisting of two camera pose estimators that deal with the information from pairwise images and a short sequence of images respectively. For image sequences, a Transformer-like structure is adopted to build a geometry model over a local temporal window, referred to as Transformer-based Auxiliary Pose …
3D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion Model
Department of Computer and Information Science, University of Macau, Macau, China（计算机与信息科学系，澳门大学，澳门，中国）；ShanghaiTech University, Shanghai, China（上海科技大学，上海，中国）
TU Wien（维也纳工业大学）；Automation and Control Institute（自动化与控制研究所）
Accurate and robust object pose estimation for robotics applications requires verification and refinement steps. In this work, we propose to integrate hypotheses verification with object pose refinement guided by physics simulation. This allows the physical plausibility of individual object pose estimates and the stability of the estimated scene to be considered in a unified optimization. The proposed method is able to adapt to scenes of multiple objects and efficiently focuses on refining the most promising object poses in multi-hypotheses scenarios. We call this integrated approach VeREFINE …
University of California, Irvine（加州大学欧文分校）；Tencent America（腾讯美国）；Amazon（亚马逊）；National Chiao Tung University（国立交通大学）
Estimating3D hand poses from RGB images is essentialto a wide range of potential applications, but is challengingowing to substantial ambiguity in the inference of depth in-formation from RGB images. State-of-the-art estimators ad-dress this problem by regularizing3D hand pose estimationmodels during training to enforce the consistency betweenthe predicted3D poses and the ground-truth depth maps.However, these estimators rely on both RGB images and thepaired depth maps during training. In this study, we proposea conditional generative adversarial network (GAN) model,called Depth-image Guided G…
University of Nevada, Reno（内华达大学里诺分校）；Stevens Institute of Technology（斯蒂文斯理工学院）
While adversarial neural networks have been shown successful for static image attacks, very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous vehicles, their mission, and environment. This paper presents an online adversarial machine learning framework that can effectively misguide autonomous vehicles' missions. In the existing image attack methods devised toward autonomous vehicles, optimization steps are repeated for every image frame. This framework removes the need for fully converged optimization …
Texas A&M University（德克萨斯农工大学）；Tencent America（腾讯美国）；Amazon Web Services（亚马逊云科技）；University of California, Irvine（加州大学欧文分校）；National Chiao Tung University（国立交通大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Estimating the 3D hand pose from a monocular RGB image is important but challenging. A solution is training on large-scale RGB hand images with accurate 3D hand keypoint annotations. However, it is too expensive in practice. Instead, we have developed a learning-based approach to synthesize realistic, diverse, and 3D pose-preserving hand images under the guidance of 3D pose information. We propose a 3D-aware multi-modal guided hand generative network (MM-Hand), together with a novel geometry-based curriculum learning strategy. Our extensive experimental results demonstrate that the 3D-annotate…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignment problem between images. At the cost of incorporating a pose estimator, many works introduce pose information to alleviate the misalignment in both training and testing. To achieve high accuracy while preserving low inference complexity, we propose a network named Pose-Guided Feature Learning with Knowledge Distillation (PGFL-KD), where the pose information is exploited to regularize the learning of semantics alig…
SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement
Faculty of Data Science, City University of Macau（数据科学学院，澳门城市大学）；College of Oceanography and Space Informatics, China University of Petroleum (East China)（海洋科学与空间信息学院，中国石油大学（华东））；School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast（电子、电气与计算机科学学院，女王大学 Belfast）；Department of Automation, Tsinghua University（自动化系，清华大学）；College of Computer Science and Software Engineering, Shenzhen University（计算机科学与软件工程学院，深圳大学）
University of Maryland - College Park（马里兰大学大学公园分校）
Human pose information is a critical component in many downstream image processing tasks, such as activity recognition and motion tracking. Likewise, a pose estimator for the illustrated character domain would provide a valuable prior for assistive content creation tasks, such as reference pose retrieval and automatic character animation. But while modern data-driven techniques have substantially improved pose estimation performance on natural images, little work has been done for illustrations. In our work, we bridge this domain gap by efficiently transfer-learning from both domain-specific a…
School of Electronics and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；Hefei Innovation Research Institute of Beihang University（北京航空航天大学合肥创新研究院）
Person re-identification (reID) aims at retrieving a person from images captured by different cameras. For deep-learning-based reID methods, it has been proved that using local features together with global feature could help to give robust representation for person retrieval. Human pose information could provide the locations of human skeleton to effectively guide the network to pay more attention on these key areas and could also help to reduce the noise distractions from background or occlusion. However, methods proposed by previous pose-based works might not be able to fully exploit the be…
Universidade da Beira Interior（贝拉内格罗大学）；Instituto de Telecomunicações（电信研究所）；DeepNeuronic（DeepNeuronic公司）
Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures seem to yield good results. This paper proposes GEA, a novel approach for guided NAS. GEA guides the evolution by exploring the search space by generating and evaluating several architectures in each generation at initialisation stage using a zero-proxy estimator, where only the highest-scoring architecture is trained and kept for the next generation. Subsequently, GEA contin…
Retinex Meets Language: A Physics-Semantics-Guided Underwater Image Enhancement Network
State Key Laboratory of Physical Oceanography and the Faculty of Information Science and Engineering, Ocean University of China（物理海洋学国家重点实验室和中国海洋大学信息科学与工程学院）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen university（中山大学深圳校区计算机科学与技术学院）
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…
