Results 91 to 100 of about 429 (147)

Splattalk: 3D VQA with Gaussian Splatting

2025 IEEE/CVF International Conference on Computer Vision (ICCV)
Language-guided 3D scene understanding is important for advancing applications in robotics, AR/VR, and human-computer interaction, enabling models to comprehend and interact with 3D environments through natural language. While 2D vision-language models (VLMs) have achieved remarkable success in 2D VQA tasks, progress in the 3D domain has been ...
Anh Thai, Songyou Peng, Kyle Genova, Leonidas J. Guibas, Thomas A. Funkhouser   +4 more
openaire   +2 more sources

Dynamic Street-Scene Reconstruction with Semantic Priors and Temporal Constraints

Applied Sciences
Dynamic street-scene reconstruction from sparse viewpoints over long temporal spans is challenged by temporal instability, ghosting near occlusions, and background drift.
Qingwu Duan, Kaichen Ren, Mingsheng Huang, Jie Liu, Siyu Li, Sili Gao   +5 more
doaj   +1 more source

Distinctive neurophysiological correlates of sound onset and offset perception in humans

The Journal of Physiology, EarlyView.
Abstract figure legend Electroencephalography (EEG) recordings were obtained from participants listening to successive pairs of 1‐2 s noises in a silent background (Study 1) or successive pairs 1‐2 s silent gaps in a noise background (Study 2). Participants heard the same stimuli in the context of either a duration discrimination task (identifying ...
Fatima Ali, Gabriela Bury, Adèle Simon, Jennifer F. Linden   +3 more
wiley   +1 more source

WildGaussians: 3D Gaussian Splatting In the Wild

Advances in Neural Information Processing Systems 37
NeurIPS 2024; Project page: https://wild-gaussians.github.io/
Kulhanek, Jonas, Peng, Songyou, Kukelova, Zuzana, Pollefeys, Marc, Sattler, Torsten   +4 more
openaire   +4 more sources

Bridging Semantic Mesh, CityGML, and Gaussian Splatting for Urban Modelling and Visualization [PDF]

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Urban digital twin systems require 3D city representations that reconcile semantic structure, geometric reliability, simulation capability, and photorealistic real-time rendering.
D. Suwardhi, D. Suwardhi, M. A. Sudibyo, A. Ambarwari, W. Andika, M. Ihsan, R. Widyastuti, W. A. Fadilah, A. Murtiyoso, P. Grussenmeyer, F. Remondino   +10 more
doaj   +1 more source

Artificial intelligence‐powered plant phenomics: Progress, challenges, and opportunities

The Plant Phenome Journal, Volume 9, Issue 1, December 2026.
Abstract Artificial intelligence (AI), a key driver of the Fourth Industrial Revolution, is being rapidly integrated into plant phenomics to automate sensing, accelerate data analysis, and support decision‐making in phenomic prediction and genomic selection.
Xu Wang, Daeun Choi, Damian Adams, Jaehyun Ahn, Kelly Balmant, Raquel Dias, Carlos D. Messina, Rafael Muñoz‐Carpena, Vance M. Whitaker, Haipeng Yu, Ziwen Yu, Chang Zhao, Changying Li   +12 more
wiley   +1 more source

Large Language Models in Electrical and Computer Engineering Education: Opportunities, Challenges and the Road Ahead

European Journal of Education, Volume 61, Issue 3, September 2026.
ABSTRACT Electrical and Computer Engineering (EE/CE) education encompasses the rigorous study of electronic systems, computing architectures, embedded platforms, signal processing and hardware–software integration. Its inherently multidisciplinary nature demands mastery of mathematical modelling and experimental validation skills that pose substantial ...
Abdulmalik Alwarafy
wiley   +1 more source

Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping

2025 IEEE/CVF International Conference on Computer Vision (ICCV)
LiDARs provide accurate geometric measurements, making them valuable for ego-motion estimation and reconstruction tasks. Although its success, managing an accurate and lightweight representation of the environment still poses challenges. Both classic and NeRF-based solutions have to trade off accuracy over memory and processing times.
Emanuele Giacomini, Luca Di Giammarino, Lorenzo De Rebotti, Giorgio Grisetti, Martin R. Oswald   +4 more
openaire   +2 more sources

GaPMeS: Gaussian Patch-Level Mixture-of-Experts Splatting for Computation-Limited Sparse-View Feed-Forward 3D Reconstruction

Applied Sciences
To address the issues of parameter coupling and high computational demands in existing feed-forward Gaussian splatting methods, we propose Gaussian Patch-level Mixture-of-Experts Splatting (GaPMeS), a lightweight feed-forward 3D Gaussian reconstruction ...
Jinwen Liu, Wenchao Liu, Rui Guo
doaj   +1 more source

Human‐in‐the‐Loop Object Segmentation for 3D Gaussian Splatting via Finger‐based VR Interface

Advanced Intelligent Systems, Volume 8, Issue 8, August 2026.
This study introduces a human‐in‐the‐loop segmentation framework for 3D Gaussian Splatting that integrates real‐time optimization with intuitive VR‐based finger prompting. Compared with existing automatic, learning‐based methods, it achieves significantly higher accuracy and reduced segmentation time.
Yongseok Lee, Hyunreal Park, Hyunsu Kim, Harim Ji, Dongho Yee, Dongjun Lee   +5 more
wiley   +1 more source