In this paper, we present a dataset capturing diverse visual data formats that target varying luminance conditions. While RGB cameras provide nourishing and intuitive information, changes in lighting conditions potentially result in catastrophic failure for robotic applications based on vision sensors. Approaches overcoming illumination problems have included developing more robust algorithms or other types of visual sensors, such as thermal and event cameras. Despite the alternative sensors' potential, there still are few datasets with alternative vision sensors. Thus, we provided a dataset recorded from alternative vision sensors, by handheld or mounted on a car, repeatedly in the same space but in different conditions. We aim to acquire visible information from co-aligned alternative vision sensors. Our sensor system collects data more independently from visible light intensity by measuring the amount of infrared dissipation, depth by structured reflection, and instantaneous temporal changes in luminance. We provide these measurements along with inertial sensors and ground-truth for developing robust visual SLAM under poor illumination. The full dataset is available at: https://visibilitydataset.github.io/
ViViD-5K: Vineyard vision dataset for field-based berry detection and segmentation and grape cluster closure estimation
Horticulture Section, School of Integrative Plant Science, Cornell University(康奈尔大学整合植物科学学院园艺系);School of Electrical and Computer Engineering, Cornell University(康奈尔大学电气与计算机工程学院)
Thermal Image Refinement with Depth Estimation using Recurrent Networks for Monocular ORB-SLAM3
Automatic Control Group (RAT), Paderborn University(自动控制组(RAT),波恩大学);Department of Electrical and Computer Engineering, Aarhus University(电气与计算机工程系,阿arhus大学);Upteko ApS(Upteko公司)
Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision
Dalian University of Technology(大连理工大学)
低光照场景下拍摄的图像往往会受到可见度低、偏色和噪声等严重影响,这些因素不仅影响图像质量,而且会降低下游低光照视觉(LLV)应用的性能。已经提出了各种深度学习方法来增强低光图像的视觉质量。然而,这些方法大多依赖于重要的建筑工程,以获得适当的低光模型,往往遭受高计算负担。此外,将这些增强技术扩展到处理其他LLV仍然具有挑战性。为了部分解决上述问题,我们建立了Retinex启发的Unrolling with Architecture Search(RUAS),这是一个通用的学习框架,它不仅可以解决弱光增强任务,而且还可以灵活地处理其他更具挑战性的下游视觉应用。具体来说,我们首先建立一个嵌套的优化配方,连同展开策略,探索一系列LLV任务的基本原则。此外,我们构建了一个可区分的策略,以合作搜索特定的场景和任务架构的RUAS。最后但并非最不重要的是,我们演示了如何将RUAS应用于低级和高级LLV应用程序(例如,增强、检测和分割)。大量的实验验证了RUAS的灵活性,有效性和效率。
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
SAIVT Group, School of Electrical Engineering and Robotics, Queensland University of Technology(澳大利亚昆士兰科技大学电气工程与机器人学院SAIVT组);CSIRO Robotics, CSIRO(澳大利亚联邦科学与工业研究组织机器人部)
Brand Visibility in Packaging: A Deep Learning Approach for Logo Detection, Saliency-Map Prediction, and Logo Placement Analysis
School of Electrical and Computer Engineering, University of Tehran, College of Engineering(德黑兰大学工程学院电气与计算机工程学院);Faculty of Electrical Engineering, K. N. Toosi University of Technology(霍加托西理工大学电气工程学院);Faculty of Engineering, Golestan University(戈尔甘大学工程学院)
From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation
Australian Institute for Machine Learning, Adelaide University(澳大利亚机器学习研究所,阿德莱德大学);Ruyi Dynamics(如意动力);Fudan University(复旦大学);Swiss Federal Institute of Technology Lausanne (EPFL)(瑞士洛桑联邦理工学院)
EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow
School of Interactive Computing, Georgia Institute of Technology(交互计算学院,佐治亚理工学院);InnoCORE AI-Transformed Aerospace Research Center, KAIST(AI转型航空航天研究中心,韩国成均馆大学)
VisionSafeEnhanced VPC: Cautious Predictive Control with Visibility Constraints under Uncertainty for Autonomous Robotic Surgery
School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院);School of Advanced Manufacturing and Robotics, Peking University(北京大学先进制造与机器人学院);MicroPort MedBot (Group) Company Ltd.(微宏医疗机器人(集团)有限公司);Department of Biomedical Engineering, City University of Hong Kong(香港城市大学生物医学工程系)
CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization
Autel Robotics(Autel机器人公司);Nanjing University(南京大学);Peking University(北京大学);Southern University of Science and Technology(南方科技大学);University of Hong Kong(香港大学)
SonarSweep: Fusing Sonar and Vision for Robust 3D Reconstruction via Plane Sweeping
Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Chinese University of Hong Kong, Hong Kong(香港中文大学);Department of Automation, Harbin Institute of Technology(哈尔滨工业大学自动化系)
VLM-CASE: Vision-Language Model Enabled Context-Adaptive Safety Envelopes for Anticipatory Safe Autonomous Driving
Department of Civil and Environmental Engineering, The Pennsylvania State University(宾夕法尼亚州立大学土木与环境工程系);Department of Civil Engineering, Stony Brook University(石溪大学土木工程系)
Assessing Vision-Language Models for Perception in Autonomous Underwater Robotic Software
Simula Research Laboratory(Simula研究实验室);Oslo Metropolitan University(奥斯陆城市大学);Mondragon University(蒙德拉贡大学);National Institute of Informatics(国立信息学研究所);Det norske Veritas (DNV)(挪威船级社(DNV))