G-SIR: Gaussian Semantic Inverse Rendering for Scaling Open-Vocabulary 3-D Understanding to City-Scale Scenes
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64, 3003221
Abstract
No abstract availableFunding Information
- Shenzhen Science and Technology Program (ZDCYKCX20250901091859001)
- “Application of Key Technologies of Precision Engineering Surveying in Urban Safety Monitoring” funded by Guangzhou Urban Planning and Design Survey Research Institute
This publication has 46 references indexed in Scilit:
- Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection2024
- Gaussian Grouping: Segment and Edit Anything in 3D Scenes2024
- CityGaussian: Real-Time High-Quality Large-Scale Scene Rendering with Gaussians2024
- FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene UnderstandingInternational Journal of Computer Vision, 2024
- An Introduction to Optimization on Smooth Manifolds2023
- Capturing, Reconstructing, and Simulating: The UrbanScene3D Dataset2022
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Geodesic Regression and the Theory of Least Squares on Riemannian ManifoldsInternational Journal of Computer Vision, 2012
- The Elements of Statistical Learning2009
- Intrinsic Statistics on Riemannian Manifolds: Basic Tools for Geometric MeasurementsJournal of Mathematical Imaging and Vision, 2006