We released the code!.

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

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: 1/3

RT @Snosixtytwo: Happy to announce the results of our latest research, which takes 3D Gaussian Splatting to the next level: "A Hierarchical….

RT @jbhuang0604: Hooray! 🤩. We just released the code of Robust Dynamic Radiance Fields (with 🔥 MIT license 🔥)! . Have fun!. .

RT @jbhuang0604: We just released the code, pretrained models (with MIT license 🔥).💻 as well as all the video data….

RT @jbhuang0604: Check out our fun work on robust view synthesis! 🤩. Using a casual video as input, our method jointly 1⃣estimates accurate….

RT @jtompkin: Do _you know_ where your cameras is? Your smartphone doesn't📵OIS can prevent RGB and ToF sensor fusion because the calibratio….

RT @Myaldiz17: Excited to release the code for our next-generation fiducial marker system, DeepformableTag!.Code: ..

RT @Myaldiz17: Introducing DeepFormableTags! .We jointly train novel #marker generation and detection networks via a photorealistic differe….