Introducing DeepFormableTags! We jointly train novel #marker generation and detection networks via a photorealistic differentiable rendering pipeline, which shows strength in motion blur and deformation. vclab.kaist.ac.kr/siggraph2021/i…  We will be presenting at #SIGGRAPH2021! (1/8)

Excited to release the code for our next-generation fiducial marker system, DeepformableTag! Code: github.com/KAIST-VCLAB/De… Colab Demo: colab.research.google.com/github/KAIST-V… Dataset: drive.google.com/drive/folders/… Project page: vclab.kaist.ac.kr/siggraph2021/i…

Do _you know_ where your cameras is? Your smartphone doesn't📵OIS can prevent RGB and ToF sensor fusion because the calibration is unknown🤷‍♀️But we can calibrate the floating camera every snapshot 📸to reduce depth RMSE through fusion from 1.08 to 0.05 🤖 - vclab.kaist.ac.kr/eccv2022/index…

Check out our fun work on robust view synthesis! 🤩 Using a casual video as input, our method jointly 1⃣estimates accurate camera poses and 2⃣reconstructs multiple local radiance fields for a large scene. Project🕸️: localrf.github.io

We just released the code, pretrained models (with MIT license 🔥) 💻 github.com/facebookresear… as well as all the video data/results used in our work 📁 drive.google.com/drive/folders/… Check out the explainer video 📹 youtu.be/VizL7q9o-5Y

Hooray! 🤩 We just released the code of Robust Dynamic Radiance Fields (with 🔥 MIT license 🔥)! Have fun! github.com/facebookresear…

Happy to announce the results of our latest research, which takes 3D Gaussian Splatting to the next level: "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets," which has been accepted at #SIGGRAPH2024!🎉 Find it here: repo-sam.inria.fr/fungraph/hiera…

We released the code! github.com/graphdeco-inri…

We are happy to announce that we are hiring a Product Engineer in Rennes, France, to help transform our on-the-fly 3D Gaussian Splatting reconstruction research into a startup! Details and application: jobs.inria.fr/public/classic…