检索结果-内蒙古大学图书馆

InstantPose: Zero-Shot Instance-Level 6D Pose Estimation From a Single View

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第6期10卷 6023-6030页

作者： Di Felice, Francesco Remus, Alberto Gasperini, Stefano Busam, Benjamin Ott, Lionel Thalhammer, Stefan Tombari, Federico Avizzano, Carlo Alberto Scuola Super Sant Anna Mech Intelligence Inst Dept Excellence Robot & AI I-56124 Pisa Italy Leonardo SpA Robot Lab Innovat Hub &I ntellectual Property I-16149 Genoa Italy Tech Univ Munich TUM Sch Computat Informat & Technol D-80809 Munich Germany Swiss Fed Inst Technol Dept Mech & Proc Engn Autonomous Syst Lab CH-8092 Zurich Switzerland UAS Tech Vienna Ind Engn Dept A-1040 Vienna Austria Google Zurich CH-8092 Zurich Switzerland

Object pose estimation using visual data is crucial for robotic interaction with the environment. Many existing instance-level methods are restricted by their requirements for 3D CAD models or multiple object views, which limits their flexibility and generalizability. Overcoming this limitation is critical to enhance the adaptability of pose estimation systems. In this work, a novel pipeline that leverages recent advances in reconstruction techniques is presented to address these challenges. To this end, Large Reconstruction Models (LRM) represent an advanced neural architecture capable of generating 3D object models from a limited set of views. Nevertheless, the resulting 3D models often lack relevant geometric and texture details due to insufficient input information. This research presents InstantPose, an innovative zero-shot instance-level pose estimation method that, building upon LRM, can determine the pose of unseen objects using as little as a single unposed RGB reference and RGB-D query images. Extensive experiments demonstrate that InstantPose achieves remarkable performance in object pose estimation on the YCB-V dataset, compared to methods conceived to rely on a geometrically perfect object's model. Furthermore, the 6D pose provided through the presented approach facilitates successful object grasping, highlighting its practical utility in robotic manipulation tasks.

关键词： Pose estimation Three-dimensional displays Solid modeling Accuracy Robots Image reconstruction Feature extraction Semantics Adaptation models Training RGB-D perception deep learning for visual perception deep learning methods

来源：评论

学校读者我要写书评

暂无评论

MonoTher-Depth: Enhancing Thermal Depth Estimation via Confidence-Aware Distillation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第3期10卷 2830-2837页

作者： Zuo, Xingxing Ranganathan, Nikhil Lee, Connor Gkioxari, Georgia Chung, Soon-Jo CALTECH Pasadena CA 91125 USA

Monocular depth estimation (MDE) from thermal images is a crucial technology for robotic systems operating in challenging conditions such as fog, smoke, and low light. The limited availability of labeled thermal data constrains the generalization capabilities of thermal MDE models compared to foundational RGB MDE models, which benefit from datasets of millions of images across diverse scenarios. To address this challenge, we introduce a novel pipeline that enhances thermal MDE through knowledge distillation from a versatile RGB MDE model. Our approach features a confidence-aware distillation method that utilizes the predicted confidence of the RGB MDE to selectively strengthen the thermal MDE model, capitalizing on the strengths of the RGB model while mitigating its weaknesses. Our method significantly improves the accuracy of the thermal MDE, independent of the availability of labeled depth supervision, and greatly expands its applicability to new scenarios. In our experiments on new scenarios without labeled depth, the proposed confidence-aware distillation method reduces the absolute relative error of thermal MDE by 22.88% compared to the baseline without distillation.

关键词： Predictive models Cameras Training Measurement Depth measurement Adaptation models Metadata Feature extraction Accuracy Uncertainty deep learning for visual perception range sensing thermal camera

来源：评论

学校读者我要写书评

暂无评论

Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第1期10卷 764-771页

作者： Lu, Yipeng Zhao, Yifan Wang, Haiping Ruan, Zhiwei Liu, Yuan Dong, Zhen Yang, Bisheng Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430072 Peoples R China China Univ Geosci Wuhan 430079 Peoples R China Didi Chuxing Technol Co Beijing 100193 Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China Nanyang Technol Univ Singapore 639798 Singapore

Dashboard cameras (dashcams) record millions of driving videos daily, offering a valuable potential data source for various applications, including driving map production and updates. A necessary step for utilizing these dashcam data involves the estimation of camera poses. However, the low-quality images captured by dashcams, characterized by motion blurs and dynamic objects, pose challenges for existing image-matching methods in accurately estimating camera poses. In this study, we propose a precise pose estimation method for dashcam images, leveraging the inherent camera motion prior. Typically, image sequences captured by dash cameras exhibit pronounced motion prior, such as forward movement or lateral turns, which serve as essential cues for correspondence estimation. Building upon this observation, we devise a pose regression module aimed at learning camera motion prior, subsequently integrating these prior into both correspondences and pose estimation processes. The experiment shows that, in real dashcams dataset, our method is 22% better than the baseline for pose estimation in AUC5 degrees, and it can estimate poses for 19% more images with less reprojection error in Structure from Motion (SfM).

关键词： Cameras Pose estimation Accuracy Feature extraction Estimation Image coding Videos Neural networks Dynamics Vectors Computer vision for transportation deep learning for visual perception SLAM

来源：评论

学校读者我要写书评

暂无评论

Bayesian NeRF: Quantifying Uncertainty With Volume Density for Neural Implicit Fields

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第3期10卷 2144-2151页

作者： Lee, Sibaek Kang, Kyeongsu Ha, Seongbo Yu, Hyeonwoo Sungkyunkwan Univ Dept Intelligent Robot Suwon 12345 South Korea

We present a Bayesian Neural Radiance Field (NeRF), which explicitly quantifies uncertainty in the volume density by modeling uncertainty in the occupancy, without the need for additional networks, making it particularly suited for challenging observations and uncontrolled image environments. NeRF diverges from traditional geometric methods by providing an enriched scene representation, rendering color and density in 3D space from various viewpoints. However, NeRF encounters limitations in addressing uncertainties solely through geometric structure information, leading to inaccuracies when interpreting scenes with insufficient real-world observations. While previous efforts have relied on auxiliary networks, we propose a series of formulation extensions to NeRF that manage uncertainties in density, both color and density, and occupancy, all without the need for additional networks. In experiments, we show that our method significantly enhances performance on RGB and depth images in the comprehensive dataset. Given that uncertainty modeling aligns well with the inherently uncertain environments of Simultaneous Localization and Mapping (SLAM), we applied our approach to SLAM systems and observed notable improvements in mapping and tracking performance. These results confirm the effectiveness of our Bayesian NeRF approach in quantifying uncertainty based on geometric structure, making it a robust solution for challenging real-world scenarios.

关键词： Uncertainty Neural radiance field Image color analysis Three-dimensional displays Bayes methods Rendering (computer graphics) Estimation Cameras Solid modeling Simultaneous localization and mapping deep learning for visual perception mapping SLAM

来源：评论

学校读者我要写书评

暂无评论

Pair-VPR: Place-Aware Pre-Training and Contrastive Pair Classification for visual Place Recognition With Vision Transformers

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第4期10卷 4013-4020页

作者： Hausler, Stephen Moghadam, Peyman CSIRO CSIRO Robot Data61 Brisbane Qld 4069 Australia Queensland Univ Technol QUT Sch Elect Engn & Robot Brisbane 4069 Australia

In this work we propose a novel joint training method for visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vision Transformer components for both the encoder and the pair classifier, and both components are trained using their respective class tokens. In existing VPR methods, typically the network is initialized using pre-trained weights from a generic image dataset such as ImageNet. In this work we propose an alternative pre-training strategy, by using Siamese Masked Image Modeling as a pre-training task. We propose a Place-aware image sampling procedure from a collection of large VPR datasets for pre-training our model, to learn visual features tuned specifically for VPR. By re-using the Mask Image Modeling encoder and decoder weights in the second stage of training, Pair-VPR can achieve state-of-the-art VPR performance across five benchmark datasets with a ViT-B encoder, along with further improvements in localization recall with larger encoders.

关键词： visual place recognition Transformers Decoding Training Image reconstruction Computer vision Benchmark testing Image recognition Data models visualization deep learning for visual perception Recognition Localization

来源：评论

学校读者我要写书评

暂无评论

Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World perception

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第2期10卷 1904-1911页

作者： Hindel, Julia Cattaneo, Daniele Valada, Abhinav Univ Freiburg Dept Comp Sci D-79110 Freiburg Germany

Semantic segmentation models are typically trained on a fixed set of classes, limiting their applicability in open-world scenarios. Class-incremental semantic segmentation aims to update models with emerging new classes while preventing catastrophic forgetting of previously learned ones. However, existing methods impose strict rigidity on old classes, reducing their effectiveness in learning new incremental classes. In this work, we propose Taxonomy-Oriented Poincar & eacute;-regularized Incremental-Class Segmentation (TOPICS) that learns feature embeddings in hyperbolic space following explicit taxonomy-tree structures. This supervision provides plasticity for old classes, updating ancestors based on new classes while integrating new classes at fitting positions. Additionally, we maintain implicit class relational constraints on the geometric basis of the Poincar & eacute;ball. This ensures that the latent space can continuously adapt to new constraints while maintaining a robust structure to combat catastrophic forgetting. We also establish eight realistic incremental learning protocols for autonomous driving scenarios, where novel classes can originate from known classes or the background. Extensive evaluations of TOPICS on the Cityscapes and Mapillary Vistas 2.0 benchmarks demonstrate that it achieves state-of-the-art performance.

关键词： Semantic segmentation Semantics Taxonomy Data models Incremental learning Training Rigidity Adaptation models visualization Predictive models Continual learning incremental learning deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

LatentBKI: Open-Dictionary Continuous Mapping in visual-Language Latent Spaces With Quantifiable Uncertainty

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第4期10卷 3102-3109页

作者： Wilson, Joey Xu, Ruihan Sun, Yile Ewen, Parker Zhu, Minghan Barton, Kira Ghaffari, Maani Univ Michigan Ann Arbor MI 48109 USA

This letter introduces a novel probabilistic mapping algorithm, LatentBKI, which enables open-vocabulary mapping with quantifiable uncertainty. Traditionally, semantic mapping algorithms focus on a fixed set of semantic categories which limits their applicability for complex robotic tasks. Vision-Language (VL) models have recently emerged as a technique to jointly model language and visual features in a latent space, enabling semantic recognition beyond a predefined, fixed set of semantic classes. LatentBKI recurrently incorporates neural embeddings from VL models into a voxel map with quantifiable uncertainty, leveraging the spatial correlations of nearby observations through Bayesian Kernel Inference (BKI). LatentBKI is evaluated against similar explicit semantic mapping and VL mapping frameworks on the popular Matterport3D and Semantic KITTI data sets, demonstrating that LatentBKI maintains the probabilistic benefits of continuous mapping with the additional benefit of open-dictionary queries. Real-world experiments demonstrate applicability to challenging indoor environments.

关键词： Uncertainty Semantics Robots Kernel Neural networks Bayes methods Probabilistic logic Three-dimensional displays Smoothing methods visualization Mapping semantic scene understanding deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

ConditionNET: learning Preconditions and Effects for Execution Monitoring

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第2期10卷 1337-1344页

作者： Sliwowski, Daniel Lee, Dongheui Tech Univ Wien TU Wien Autonomous Syst Lab A-1040 Vienna Austria Inst Robot & Mechatron DLR German Aerosp Ctr D-82234 Wessling Germany

The introduction of robots into everyday scenarios necessitates algorithms capable of monitoring the execution of tasks. In this letter, we propose ConditionNET, an approach for learning the preconditions and effects of actions in a fully data-driven manner. We develop an efficient vision-language model and introduce additional optimization objectives during training to optimize for consistent feature representations. ConditionNET explicitly models the dependencies between actions, preconditions, and effects, leading to improved performance. We evaluate our model on two robotic datasets, one of which we collected for this letter, containing 406 successful and 138 failed teleoperated demonstrations of a Franka Emika Panda robot performing tasks like pouring and cleaning the counter. We show in our experiments that ConditionNET outperforms all baselines on both anomaly detection and phase prediction tasks. Furthermore, we implement an action monitoring system on a real robot to demonstrate the practical applicability of the learned preconditions and effects. Our results highlight the potential of ConditionNET for enhancing the reliability and adaptability of robots in real-world environments.

关键词： Robot sensing systems Monitoring Feature extraction Hidden Markov models Planning Probabilistic logic Natural languages Image segmentation Anomaly detection Transformers deep learning methods data sets for robot learning deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第4期10卷 3462-3469页

作者： Kim, Jaeyeul Woo, Jungwan Shin, Ukcheol Oh, Jean Im, Sunghoon DGIST Dept Elect Engn & Comp Sci Daegu 42988 South Korea Carnegie Mellon Univ Robot Inst Pittsburgh PA 15217 USA

Understanding the motion states of the surrounding environment is critical for safe autonomous driving. These motion states can be accurately derived from scene flow, which captures the three-dimensional motion field of points. Existing LiDAR scene flow methods extract spatial features from each point cloud and then fuse them channel-wise, resulting in the implicit extraction of spatio-temporal features. Furthermore, they utilize 2D Bird's Eye View and process only two frames, missing crucial spatial information along the Z-axis and the broader temporal context, leading to suboptimal performance. To address these limitations, we propose Flow4D, which temporally fuses multiple point clouds after the 3D intra-voxel feature encoder, enabling more explicit extraction of spatio-temporal features through a 4D voxel network. However, while using 4D convolution improves performance, it significantly increases the computational load. For further efficiency, we introduce the Spatio-Temporal Decomposition Block (STDB), which combines 3D and 1D convolutions instead of using heavy 4D convolution. In addition, Flow4D further improves performance by using five frames to take advantage of richer temporal information. As a result, the proposed method achieves a 45.9% higher performance compared to the state-of-the-art while running in real-time, and won 1st place in the 2024 Argoverse 2 Scene Flow Challenge.

关键词： Feature extraction Point cloud compression Three-dimensional displays Convolution Data mining Laser radar Estimation Vectors Fuses Real-time systems Computer vision for transportation deep learning for visual perception recognition

来源：评论

学校读者我要写书评

暂无评论

CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic perception of Driving Scenes

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第4期10卷 3134-3141页

作者： Brodermann, Tim Sakaridis, Christos Fu, Yuqian Van Gool, Luc Swiss Fed Inst Technol Comp Vis Lab CH-8057 Zurich Switzerland Sofia Univ St Kliment Ohridski INSAIT Sofia 1504 Bulgaria

Leveraging multiple sensors is crucial for robust semantic perception in autonomous driving, as each sensor type has complementary strengths and weaknesses. However, existing sensor fusion methods often treat sensors uniformly across all conditions, leading to suboptimal performance. By contrast, we propose a novel, condition-aware multimodal fusion approach for robust semantic perception of driving scenes. Our method, CAFuser, uses an RGB camera input to classify environmental conditions and generate a Condition Token that guides the fusion of multiple sensor modalities. We further newly introduce modality-specific feature adapters to align diverse sensor inputs into a shared latent space, enabling efficient integration with a single and shared pre-trained backbone. By dynamically adapting sensor fusion based on the actual condition, our model significantly improves robustness and accuracy, especially in adverse-condition scenarios. CAFuser ranks first on the public MUSES benchmarks, achieving 59.7 PQ for multimodal panoptic and 78.2 mIoU for semantic segmentation, and also sets the new state of the art on DeLiVER.

关键词： Sensors Sensor fusion Semantics Adaptation models Cameras Feature extraction Laser radar Radar Meteorology Semantic segmentation semantic scene understanding computer vision for transportation deep learning for visual perception multimodal semantic perception

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：