MeGAS augments 3D Gaussian Splatting with temperature attributes, heat advection-diffusion, and MPM phase transitions to produce physically consistent thermomechanical scene behavior while preserving photorealistic rendering.
arXiv preprint arXiv:2409.07200 (2024)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
LIT-GS adds LiDAR plane geometry constraints and thermal-LiDAR cross-modal anchors to Gaussian Splatting for improved geometric accuracy and rendering under varying illumination.
DarkVGGT introduces physics-aware thermal factorization and geometry-shared routing modules in an RGB-T feed-forward framework to improve depth and camera pose estimation under degraded RGB conditions.
TDg derives thermal radiance fields from thermal images and depth estimation, reporting minor gains over the MSMG baseline (LPIPS +1.12%, SSIM +0.034%, PSNR +0.01%) and 55% faster training on two datasets.
citing papers explorer
-
MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing
MeGAS augments 3D Gaussian Splatting with temperature attributes, heat advection-diffusion, and MPM phase transitions to produce physically consistent thermomechanical scene behavior while preserving photorealistic rendering.
-
LIT-GS: LiDAR-Inertial-Thermal Gaussian Splatting for Illumination-Robust Mapping
LIT-GS adds LiDAR plane geometry constraints and thermal-LiDAR cross-modal anchors to Gaussian Splatting for improved geometric accuracy and rendering under varying illumination.
-
DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax
DarkVGGT introduces physics-aware thermal factorization and geometry-shared routing modules in an RGB-T feed-forward framework to improve depth and camera pose estimation under degraded RGB conditions.
-
Supercharging Thermal Gaussian Splatting with Depth Estimation
TDg derives thermal radiance fields from thermal images and depth estimation, reporting minor gains over the MSMG baseline (LPIPS +1.12%, SSIM +0.034%, PSNR +0.01%) and 55% faster training on two datasets.