检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Burde, Varun Moroz, Artem Zeman, Vít Burget, Pavel Czech Technical University Prague Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Republic

Object pose estimation is a prominent task in computer vision. The object pose gives the orientation and translation of the object in real-world space, which allows various applications such as manipulation, augmented reality, etc. Various objects exhibit different properties with light, such as reflections, absorption, etc. This makes it challenging to understand the object’s structure in RGB and depth channels. Recent research has been moving toward learning-based methods, which provide a more flexible and generalizable approach to object pose estimation utilizing deep learning. One such approach is the render-and-compare method, which renders the object from multiple views and compares it against the given 2D image, which often requires an object representation in the form of a CAD model. We reason that the synthetic texture of the CAD model may not be ideal for rendering and comparing operations. We showed that if the object is represented as an implicit (neural) representation in the form of Neural Radiance Field (NeRF), it exhibits a more realistic rendering of the actual scene and retains the crucial spatial features, which makes the comparison more versatile. We evaluated our NeRF implementation of the render-and-compare method on transparent datasets and found that it surpassed the current state-of-the-art results. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

WildGaussians: 3D Gaussian Splatting in the Wild 38

WildGaussians: 3D Gaussian Splatting in the Wild

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kulhanek, Jonas Peng, Songyou Kukelova, Zuzana Pollefeys, Marc Sattler, Torsten Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Czech Republic Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic Department of Computer Science ETH Zurich Switzerland Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic

While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LEARNING TO DESIGN PROTEIN-PROTEIN INTERACTIONS WITH ENHANCED GENERALIZATION 12

LEARNING TO DESIGN PROTEIN-PROTEIN INTERACTIONS WITH ENHANCE...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Bushuiev, Anton Bushuiev, Roman Kouba, Petr Filkin, Anatolii Gabrielova, Marketa Gabriel, Michal Sedlar, Jiri Pluskal, Tomas Damborsky, Jiri Mazurenko, Stanislav Sivic, Josef Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic Loschmidt Laboratories Department of Experimental Biology and RECETOX Masaryk University Czech Republic International Clinical Research Center St. Anne's University Hospital Brno Czech Republic Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences Czech Republic

Discovering mutations enhancing protein-protein interactions (PPIs) is critical for advancing biomedical research and developing improved therapeutics. While machine learning approaches have substantially advanced the field, they often struggle to generalize beyond training data in practical scenarios. The contributions of this work are three-fold. First, we construct PPIRef, the largest and non-redundant dataset of 3D protein-protein interactions, enabling effective large-scale learning. Second, we leverage the PPIRef dataset to pre-train PPIformer, a new SE(3)equivariant model generalizing across diverse protein-binder variants. We fine-tune PPIformer to predict effects of mutations on protein-protein interactions via a thermodynamically motivated adjustment of the pre-training loss function. Finally, we demonstrate the enhanced generalization of our new PPIformer approach by outperforming other state-of-the-art methods on new, non-leaking splits of standard labeled PPI mutational data and independent case studies optimizing a human antibody against SARS-CoV-2 and increasing the thrombolytic activity of staphylokinase. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement

The Unreasonable Effectiveness of Pre-Trained Features for C...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Gabriele Trivigno Carlo Masone Barbara Caputo Torsten Sattler Politecnico di Torino Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Pose refinement is an interesting and practically rele-vant research direction. Pose refinement can be used to (1) obtain a more accurate pose estimate from an initial prior (e.g., from retrieval), (2) as pre-processing, i.e., to provide a better starting point to a more expensive pose estimator, (3) as post-processing of a more accurate local-izer. Existing approaches focus on learning features / scene representations for the pose refinement task. This involves training an implicit scene representation or learning features while optimizing a camera pose-based loss. A natural question is whether training specific features / representations is truly necessary or whether similar results can be al-ready achieved with more generic features. In this work, we present a simple approach that combines pre-trained features with a particle filter and a renderable representation of the scene. Despite its simplicity, it achieves state-of-the-art results, demonstrating that one can easily build a pose refiner without the need for specific training. The code is at https://***/gali130/mcloc_poseref

关键词： Training Location awareness Computer vision Accuracy Codes Buildings Cameras

来源：评论

学校读者我要写书评

暂无评论

Communicating human intent to a robotic companion by multi-type gesture sentences

Communicating human intent to a robotic companion by multi-t...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Petr Vanc Jan Kristof Behrens Karla Stepanova Vaclav Hlavac Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics

Human-Robot collaboration in home and industrial workspaces is on the rise. However, the communication between robots and humans is a bottleneck. Although people use a combination of different types of gestures to complement speech, only a few robotic systems utilize gestures for communication. In this paper, we propose a gesture pseudo-language and show how multiple types of gestures can be combined to express human intent to a robot (i.e., expressing both the desired action and its parameters - e.g., pointing to an object and showing that the object should be emptied into a bowl). The demonstrated gestures and the perceived tabletop scene (object poses detected by CosyPose) are processed in real-time) to extract the human's intent. We utilize behavior trees to generate reactive robot behavior that handles various possible states of the world (e.g., a drawer has to be opened before an object is placed into it) and recovers from errors (e.g., when the scene changes). Furthermore, our system enables switching between direct teleoperation of the end-effector and high-level operation using the proposed gesture sentences. The system is evaluated on increasingly complex tasks using a real 7-DoF Franka Emika Panda manipulator. Controlling the robot via action gestures lowered the execution time by up to 60%, compared to direct teleoperation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Context-aware robot control using gesture episodes

Context-aware robot control using gesture episodes

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Petr Vanc Jan Kristof Behrens Karla Stepanova Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics

Collaborative robots became a popular tool for increasing productivity in partly automated manufacturing plants. Intuitive robot teaching methods are required to quickly and flexibly adapt the robot programs to new tasks. Gestures have an essential role in human communication. However, in human-robot-interaction scenarios, gesture-based user interfaces are so far used rarely, and if they employ a one-to-one mapping of gestures to robot control variables. In this paper, we propose a method that infers the user's intent based on gesture episodes, the context of the situation, and common sense. The approach is evaluated in a simulated table-top manipulation setting. We conduct deterministic experiments with simulated users and show that the system can even handle the personal preferences of each user.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pipeline for Population and Analysis of Personal Health Knowledge Graphs (PHKGs) 18

A Pipeline for Population and Analysis of Personal Health Kn...

引用

18th International Conference on Semantic Systems, SEMPDW 2022

作者： Bosanska, Dagmar Celuchova Huptych, Michal Lhotská, Lenka Faculty of Biomedical Engineering Czech Technical University Prague Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Czech Republic

Personal Health Knowledge Graphs (PHKGs) are not yet ubiquitous, even though they have a great potential to enrich general knowledge captured in various Knowledge Graphs by adding personal contexts. This poster paper presents work in progress about a pipeline for generating PHKGs from tree-structured Electronic Health Record (EHR) data by applying a hierarchical ontological approach. This pipeline could also be applied to other domains of Personal Knowledge Graphs. Moreover, this pipeline targets the intersection between the symbolic representation of knowledge used for computational semantics and numeric graph data representation used for graph analysis and machine learning. We present the first results from applying this pipeline to synthetic patient EHRs with the diagnosis of colorectal cancer (based on Synthea). The resulting numeric representation of PHKGs or their subgraphs can be used in many practical graph algorithms. Finally, our pipeline study uncovers future research on how this numeric representation of PHKGs should be embedded into continuous and low-dimensional vector space to utilize graph machine learning and deep learning methods. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

ILeSiA: Interactive Learning of Situational Awareness from Camera Input

arXiv

引用

arXiv 2024年

作者： Vanc, Petr Franzese, Giovanni Behrens, Jan Kristof Santina, Cosimo Della Stepanova, Karla Kober, Jens Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Czech Republic Cognitive Robotics Delft University of Technology Netherlands

Learning from demonstration is a promising way of teaching robots new skills. However, a central problem when executing acquired skills is to recognize risks and failures. This is essential since the demonstrations usually cover only a few mostly successful cases. Inevitable errors during execution require specific reactions that were not apparent in the demonstrations. In this paper, we focus on teaching the robot situational awareness from an initial skill demonstration via kinesthetic teaching and sparse labeling of autonomous skill executions as safe or risky. At runtime, our system, called ILeSiA, detects risks based on the perceived camera images by encoding the images into a low-dimensional latent space representation and training a classifier based on the encoding and the provided labels. In this way, ILeSiA boosts the confidence and safety with which robotic skills can be executed. Our experiments demonstrate that classifiers, trained with only a small amount of user-provided data, can successfully detect numerous risks. The system is flexible because the risk cases are defined by labeling data. This also means that labels can be added as soon as risks are identified by a human supervisor. We provide all code and data required to reproduce our experiments at ***/publications/ilesia. © 2024, CC BY-NC-SA.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Context-aware robot control using gesture episodes

arXiv

引用

arXiv 2023年

作者： Vanc, Petr Behrens, Jan Kristof Stepanova, Karla Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Czech Republic

Collaborative robots became a popular tool for increasing productivity in partly automated manufacturing plants. Intuitive robot teaching methods are required to quickly and flexibly adapt the robot programs to new tasks. Gestures have an essential role in human communication. However, in human-robot-interaction scenarios, gesture-based user interfaces are so far used rarely, and if they employ a one-to-one mapping of gestures to robot control variables. In this paper, we propose a method that infers the user’s intent based on gesture episodes, the context of the situation, and common sense. The approach is evaluated in a simulated table-top manipulation setting. We conduct deterministic experiments with simulated users and show that the system can even handle personal preferences of each user. © 2023, CC BY-NC-SA.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Influence of Relative Power Difference Weighting on Convergence of Coupled Neutronic Thermal-Hydraulic Calculations of Heavy Water Small Modular Reactor 20

Influence of Relative Power Difference Weighting on Converge...

引用

20th International Topical Meeting on Nuclear Reactor Thermal Hydraulics, NURETH 2023

作者： Korinek, T. Skoda, R. Lovecky, M. Zavorka, J. Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Jugoslavskych partyzanu 1580/3 Prague 6160 00 Czech Republic University of West Bohemia Univerzitni 8 Pilsen316 00 Czech Republic

ISBN: (纸本)9780894487934

A heavy water reactor with pressure tubes contains a low-pressure moderator system separated from a pressurized coolant system. The moderator is heated from radiation heating during the reactor full power operation where the heat is approximately 5 % of the reactor power. The present study deals with full-core multi-physics calculations using coupled neutronic and thermal-hydraulics codes on a heavy water small modular reactor (SMR) concept for district heating applications. The full-core coupled calculations are realized using Picard iterations. The main objective of the study is to analyze the convergence of coupled calculations with particular interest on power difference weighting. The power distribution difference in fuel is weighted with a relative power of fuel pins and several methods are analyzed for weighting of heat generated in the moderator. The evaluation of heat distribution difference in the moderator is crucial for overall convergence of coupled calculations as a small difference in the moderator heat source would lead to a change of temperature and flow fields and a slow convergence, especially for a buoyant dominated flow in the moderator vessel. © 2023 Proceedings of the 20th International Topical Meeting on Nuclear Reactor Thermal Hydraulics, NURETH 2023. All rights reserved.

关键词： Heavy water reactors

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：