At

📢 We show how to transfer appearance between assets of significant geometric difference, e.g., between a giraffe 🦒 and a chair 🪑. Our method guides pre-trained rectified flow models for robust, geometry-aware 3D appearance transfer between objects.

Do you need more data for your supervised models? Our SCANnotate++ provides high-quality CAD model annotations for ScanNet++. Models trained on our automatic annotations achieve good performance for point cloud completion and single-view CAD model retrieval and alignment.

PyTorchGeoNodes is now on GitHub: github.com/vevenom/pytorc… PyTorchGeoNodes is a differentiable module for reconstructing 3D objects from images using interpretable shape programs. Collaboration with: Stefan Ainetter Mattia D’Urso Friedrich Fraundorfer

Just randomly ran into this post at medium.com: medium.com/@mayankprashar… I am super happy to read that students at

did a great job reimplementing our MonteFloor 🫡😊They even did some additional analysis to highlight potential issues of our approach 😅

All this progress in VR technology just so we can travel time and play cool games from 80s / 90s but without air blowing the cartridges, I love it😄 Now, let's do the same for AR!