all AI news logo
all AI news - Your AI news aggregator
Log in Sign up
all AI news

Gaussian Splatting SLAM

Add to bookmarks
April 16, 2024, 4:49 a.m. | Hidenobu Matsuki, Riku Murai, Paul H. J. Kelly, Andrew J. Davison

cs.CV updates on arXiv.org arxiv.org

arXiv:2312.06741v2 Announce Type: replace
Abstract: We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the required representation for accurate, efficient tracking, mapping, and high-quality rendering. Designed for challenging monocular settings, our approach is seamlessly extendable to RGB-D SLAM when an external depth sensor is available. Several innovations are required to continuously reconstruct …

abstract application arxiv cs.cv cs.ro mapping quality rendering representation setup slam tracking type visual visual slam

Visit resource

More from arxiv.org / cs.CV updates on arXiv.org

Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms 15 hours ago | arxiv.org
abstract arxiv cases cs.cv +13
PREGO: online mistake detection in PRocedural EGOcentric videos 15 hours ago | arxiv.org
abstract applications arxiv capability +12
Uncertainty estimates for semantic segmentation: providing enhanced reliability for automated motor claims handling 15 hours ago | arxiv.org
abstract arxiv automated automation +17
CG-HOI: Contact-Guided 3D Human-Object Interaction Generation 15 hours ago | arxiv.org
abstract arxiv cs.cv dynamic +9
DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection 15 hours ago | arxiv.org
abstract alignment arxiv bias +14
ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models 15 hours ago | arxiv.org
abstract arxiv capabilities commonsense +21
REB: Reducing Biases in Representation for Industrial Anomaly Detection 15 hours ago | arxiv.org
anomaly anomaly detection arxiv biases +7
Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems 15 hours ago | arxiv.org
arxiv block bridge cs.ai +11
Multicenter Privacy-Preserving Model Training for Deep Learning Brain Metastases Autosegmentation 15 hours ago | arxiv.org
abstract arxiv brain cs.cv +16

Jobs in AI, ML, Big Data

Post a Job Search Talent

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote
View on ai-jobs.net

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote
View on ai-jobs.net

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote
View on ai-jobs.net

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
View on ai-jobs.net

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX
View on ai-jobs.net

Lead Developer (AI)

@ Cere Network | San Francisco, US
View on ai-jobs.net