Results 51 to 60 of about 14,258 (262)
Outdoor Scene Understanding Based on Multi-Scale PBA Image Features and Point Cloud Features
Sensors, 2019 Outdoor scene understanding based on the results of point cloud classification plays an important role in mobile robots and autonomous vehicles equipped with a light detection and ranging (LiDAR) system.
Yisha Liu +3 more
doaj +1 more source
Bioinspired Adaptive Sensors: A Review on Current Developments in Theory and Application
Advanced Materials, EarlyView.This review comprehensively summarizes the recent progress in the design and fabrication of sensory‐adaptation‐inspired devices and highlights their valuable applications in electronic skin, wearable electronics, and machine vision. The existing challenges and future directions are addressed in aspects such as device performance optimization ...
Guodong Gong +12 more
wiley +1 more source
Gaussian-UDSR: Real-Time Unbounded Dynamic Scene Reconstruction with 3D Gaussian Splatting
Applied SciencesUnbounded dynamic scene reconstruction is crucial for applications such as autonomous driving, robotics, and virtual reality. However, existing methods struggle to reconstruct dynamic scenes in unbounded outdoor environments due to challenges such as ...
Yang Sun +5 more
doaj +1 more source
Opportunities of Semiconducting Oxide Nanostructures as Advanced Luminescent Materials in Photonics
Advanced Materials, EarlyView.The review discusses the challenges of wide and ultrawide bandgap semiconducting oxides as a suitable material platform for photonics. They offer great versatility in terms of tuning microstructure, native defects, doping, anisotropy, and micro‐ and nano‐structuring. The review focuses on their light emission, light‐confinement in optical cavities, and
Ana Cremades +7 more
wiley +1 more source
Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
CoRREnabling agents to understand and interact with complex 3D scenes is a fundamental challenge for embodied artificial intelligence systems. While Multimodal Large Language Models (MLLMs) have achieved significant progress in 2D image understanding, extending such capabilities to 3D scenes remains difficult: 1) 3D environment involves richer concepts ...
Haoyuan Li +3 more
openaire +2 more sources
Pose2Room: Understanding 3D Scenes from Human Activities
, 2022 With wearable IMU sensors, one can estimate human poses from wearable devices without requiring visual input~\cite{von2017sparse}. In this work, we pose the question: Can we reason about object structure in real-world environments solely from human trajectory information?
Yinyu Nie +3 more
openaire +2 more sources
Advanced Materials, EarlyView.We mechanically program liquid crystal elastomer coatings as a stimuli‐responsive and digitally addressable platform for refreshable tactile displays; we validate the perceptual performance of our dynamic device matches conventional static tactile media.
Tom Bruining +9 more
wiley +1 more source
Latent 3D Volume for Joint Depth Estimation and Semantic Segmentation from a Single Image
Sensors, 2020 This paper proposes a novel 3D representation, namely, a latent 3D volume, for joint depth estimation and semantic segmentation. Most previous studies encoded an input scene (typically given as a 2D image) into a set of feature vectors arranged over a 2D
Seiya Ito, Naoshi Kaneko, Kazuhiko Sumi
doaj +1 more source
Semantic segmentation-assisted instance feature fusion for multi-level 3D part instance segmentation
Computational Visual Media, 2023 Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding. Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further exploit the inherent
Chun-Yu Sun, Xin Tong, Yang Liu
doaj +1 more source
Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback
Advanced Robotics Research, EarlyView.BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat +4 more
wiley +1 more source