Federico Tombari

Google Internship call: we are looking for a PhD student in the area of object/scene understanding and VLMs to join our Google team in Zurich next summer. If you have applied for the 2025 Google Internship Call already and are interested to know more, ping me!

Excited to share LoRACLR, a new way to compose from multiple LoRA models. A collaboration with Google Research!

🚀 Excited to share our preprint LoRACLR! TL;DR: LoRACLR merges multiple LoRA models into a unified diffusion model for seamless, high-fidelity multi-concept image synthesis with minimal interference. Thanks to @THofmann2017, @fedassa, and @PINguAR! 🙌

Super happy to announce that Stylebreeder🎨 has been accepted to NeurIPS! Congratulations to the incredible students Matt (who worked on this as an undergrad at VT), Enis @enisimsar, Hidir @d_yesiltepe, and our collaborators @fedassa and @_joelsimon! stylebreeder.github.io

#SG2RL returns to @ICCVConference 2025 at Honolulu, Hawai'i 🌴☀️ We call for full papers and extended abstracts on all topics around graphs and scene graphs. Deadline: 26 June (23:59PT) Website: sites.google.com/view/sg2rl With our amazing co-organizers: @eadeli @ir0armeni @fedassa

Huge thanks to the amazing team: @Weiyu_Liu_ (co-lead), Siyi Gu, @dill_pkl , Goutam Bhat, @fedassa , @ManlingLi_ , @nickhaber , @jiajunwu_cs 🌐Project site: ai.stanford.edu/~sunfanyun/lay… 💻 Code (we plan to open-source everything): github.com/sunfanyunn/Lay… n/n

Excited to see our paper "Tokenformer: Rethinking transformer scaling with tokenized model parameters" accepted as a spotlight at #ICLR2025 ! Hope our idea of ​​tokenizing everything can inspire the future of AI. Paper: arxiv.org/abs/2410.23168 Code: github.com/Haiyang-W/Toke…

Joint work with Fan Yue, @ferjadnaeem, @xyongqin, @janericlenssen, Liwei Wang, @fedassa, and Bernt Schiele. Thanks to everyone on that amazing team.😉😀

🚀 Excited to introduce UIP2P: Unsupervised Instruction-Based Image Editing via Cycle Edit Consistency (CEC)! TL;DR: Scalable instruction-based image editing without paired image data. Works on real-world datasets with robust, reversible edits! Thanks to Alessio Tonioni,…

Get ready for the next @CVPR workshop on OpenWorld 3D Scene Understanding ➡️ opensun3d.github.io We will be hosting: - prized challenge 🏆 (see scenefun3d.github.io) - paper track 🗞️ - exciting keynote speakers  👩‍🏫 #CVPR2025

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians Contributions: • We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models. • We introduce the…

#AndroidXR is officially here! 🎉 Thrilled to see the developer excitement and passion to build immersive experiences. Huge thanks to the @GoogleARVR team and our incredible partners @SamsungMobile and @Qualcomm and more. ➡️ blog.google/products/andro…

Thrilled to share our latest work showing that “distillation through data” can be more effective than traditional knowledge-distillation (KD) for efficient multimodal pretraining- our distilled models have achieve SoTA performance at less inference cost! arxiv.org/abs/2411.18674

📣 Google/ETH PhD position available The group of Prof Schindler at ETH offers a fully funded PhD position in collaboration with our team at Google on the topic of 3D computer vision and generative models. For more details (including how to apply): jobs.ethz.ch/job/view/JOPG_…

We are just two days away from our RSS’24 Workshop on Semantics for Robotics! Check out our lineup of speakers and join us on Monday, July 15 @ 8:45 CEST: tiny.cc/rss24-sfr-work… 🏠 Location: Lecture Hall D, Aula Conference Centre, TU Delft 🌐 Livestream: tiny.cc/rss24-sfr-yout…

Check out the online demo for #OpenNeRF ✨ ➡️ opennerf.github.io/demo.html 🚀 📄Paper: arxiv.org/abs/2404.03650 👩‍💻Code: github.com/opennerf/openn… 📽️ Project: opennerf.github.io \w @fedassa @mapo1 @Mi_Niemeyer et al. @iclr_conf @ETH_en @ETH_AI_Center @GoogleAI

Congrats Ege and all co-authors for winning this award - go scene graphs!

Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos @Stearns2Colton, @AdamWHarley, @mikacuy, @fpgDubost, @fedassa, @GordonWetzstein, @GuibasLeonidas tl;dr: isotropic Gaussian “marbles”+divide-and-conquer learning+2D&3D priors arxiv.org/pdf/2406.18717

Stylebreeder Exploring and Democratizing Artistic Styles through Text-to-Image Models Text-to-image models are becoming increasingly popular, revolutionizing the landscape of digital art creation by enabling highly detailed and creative visual content generation. These

Today @AlexDelitzas✨presents #SceneFun3D the first large-scale 3D dataset with realistic interaction & functionality labels in 3D spaces🚀 🗣️Oral: 3D_Vision 1pm, Summit 🌆Poster: 342 5pm, Arch cvpr.thecvf.com/virtual/2024/o… w/ @mapo1 @fedassa @aycatakmaz #CVPR24 @GoogleAI @ETH_en