Another amazing result from our GraphDeco group at @inria_sophia. Our method solves the drift and loop closure problems for immediate 3DGS capture, and handles big scenes. Congratulations to @AndreasMeuleman and the rest of the team! Go see the talk at @siggraph next week, Thu pm

I am very excited to be part of OnTheFly, a startup we are spinning off based on research developed at our GraphDeco team at Inria. Our ambition: easy 3D capture for everyone, everywhere! Visit the booth at @siggraph next week to talk to @AndreasMeuleman and @CamilleMontemagni

Last week at EGSR my talented Ph.D. student Ishaan Shah presented his work on using modern tools to precompute global illumination (journal track): with 4-8min precomputation, we get real-time global illumination in challenging scenes! repo-sam.inria.fr/nerphys/pb…

We are excited to announce our work on efficient precomputation for real-time global illumination, presented at EGSR'26 last week! Learn more: repo-sam.inria.fr/nerphys/pb…. This work was conducted with @SimonLUCAS_CG and @GDrettakis. Funded by the ERC Advanced Grant NERPHYS.

Checkout our new SIGGRAPH Asia 2025 paper: repo-sam.inria.fr/nerphys/ed…. For more details see linkedin.com/posts/george-dr…

This work was conducted with @ishaan_n_shah, @alanvinx, @Snosixtytwo, and @GDrettakis. Special thanks to @jefequien for setting up the phone-based capture. Funded by the European Research Council (ERC) Advanced Grant NERPHYS, number 101141721 project.inria.fr/nerphys.

We introduce a fast and scalable on-the-fly 3D Gaussian Splatting method that simultaneously estimates poses and reconstructs scenes, making your 3DGS reconstruction available immediately after capturing your photos. 2/3

We are very excited to announce our work "On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images", to be presented at #SIGGRAPH2025! Learn more: repo-sam.inria.fr/nerphys/on… 1/3

With our work "Reducing the Memory Footprint of 3D Gaussian Splatting," a method that reduces the size of 3DGS from several hundreds to just a few tens of MBs, you now have more space available for additional scenes! For more, check out our project page repo-sam.inria.fr/fungraph/r…