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/reduc…

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-the… 1/3

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

This work was conducted with Ishaan Shah, Alexandre Lanvin, Bernhard Kerbl, and George Drettakis. Special thanks to Jeffrey Hu for setting up the phone-based capture. Funded by the European Research Council (ERC) Advanced Grant NERPHYS, number 101141721 project.inria.fr/nerphys.