preacherwhite/ODE-GS
[ICLR 2026] ODE-GS: Latent ODEs for Dynamic Scene Extrapolation with 3D Gaussian Splatting
Python14 stars3 forks
Topics
#3d-gaussian-splatting#computer-vision#dynamic-scene-reconstruction#gaussian-splatting#iclr-2026#neural-ode#pytorch#scene-extrapolation
What it does
ODE-GS is an implementation of a novel approach using Latent ODEs for dynamic scene extrapolation, enhancing the capabilities of 3D Gaussian splatting. This method is significant for advancing computer vision and graphics applications, particularly in generating realistic scene extrapolations from limited data.
Star history
Tracking
- Last trending
- 2026-02-21
Creator kit
Hook
Explore cutting-edge techniques in dynamic scene extrapolation with ODE-GS and transform your understanding of 3D Gaussian splatting!
Content angles
- A tutorial on setting up and using ODE-GS for scene extrapolation.
- An analysis of the performance of ODE-GS compared to traditional methods.
- A case study showcasing real-world applications of dynamic scene extrapolation.
Who should care
Researchers and developers in AI, computer vision, and graphics looking to enhance scene generation techniques.