Research map / 3D vision / Gaussian splatting
DTGS: Physics-Embedded Dynamic Thermal 3D Reconstruction with Gaussian Splatting
Junbo Li, Hang Fu, Yinuo Wang, Weimin Yuan, Cai Meng, Xiangzhi Bai
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes DTGS, a physics-embedded Gaussian splatting method for dynamic thermal infrared 3D reconstruction that addresses atmospheric transport effects and low-emissivity interference.
Problem
Dynamic 3D reconstruction in thermal infrared scenes is difficult because of atmospheric transport effects and interference from low-emissivity surfaces.
Approach
Embeds thermal physics into a dynamic Gaussian splatting representation so that reconstruction accounts for atmospheric transport and emissivity effects; specific mechanism not stated in the abstract.
Closest papers by meaning
- ThermalGaussian: Thermal 3D Gaussian Splatting (ICLR 2025 · similarity 0.90)
- NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics (CVPR 2025 · similarity 0.89)
- SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes (CVPR 2025 · similarity 0.87)
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos (NeurIPS 2025 · similarity 0.87)
- From Chaos to Clarity: 3DGS in the Dark (NeurIPS 2024 · similarity 0.86)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
