3D Fire Reconstruction Achieved with Gaussian Splatting and Optical Flow

Researchers have developed a novel method for reconstructing dynamic fire in 3D using a spatiotemporal representation based on Gaussian functions. This technique aims to capture the complex, high-frequency features of fire from a limited number of camera views by separating the static background from the volatile fire region. The system utilizes dense multi-view stereo images, monocular depth priors, and a 3D flow field derived from optical flow to initialize the fire, with individual 3D Gaussians encoding lifetime and velocity for accurate temporal alignment. AI

IMPACT This research advances 3D reconstruction techniques, potentially impacting fields requiring realistic dynamic scene rendering.

RANK_REASON The cluster contains a research paper detailing a new method for 3D reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• 3D Gaussian splatting
• arXiv
• cs.CV
• Gaussian function
• Gaussians on Fire: High-Frequency Reconstruction of Flames
• Jakob Nazarenus
• monocular depth priors
• optical flow

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →