Honourable Mention ICCV2021 Viewing Graph Solvability via Cycle Consistency Federica Arrigoni (University of Trento), Andrea Fusiello, Elisa, Tomas Pajdla [Session 5 A/B]

Our paper "Self-Supervised Models are Continual Learners" (arxiv.org/abs/2112.04215) was accepted at #CVPR2022. We uploaded the camera-ready version on arXiv and released the code on GitHub (github.com/DonkeyShot21/c…) Victor Turrisi Xavier Alameda-Pineda (ell/he/lui) Elisa Ricci Karteek Alahari Julien Mairal

Check out our group's latest CVPR22 work!

Check out AutoRF: Learning 3D Object Radiance Fields from Single View Observations #CVPR2022 by Norman Müller. Key idea: we learn shape & appearance priors from single-view training samples by exploiting machine-annotated labels! sirwyver.github.io/AutoRF/ youtu.be/mDcsSK3GaF4

Bored just staring at 3D bounding boxes? We generate renderable 3D representations from only single-view observations in our latest #CVPR2022 paper. Great collaboration Andrea Simonelli, Lorenzo Porzi, Samuel Rota Bulò, and Peter Kontschieder from Reality Labs at Meta and Matthias Niessner

I'm looking for a summer/fall intern working at Mila - Institut québécois d'IA on speaker recognition and diarization using #SpeechBrain. If you have expertise in this field (with relevant publications) feel free to apply as soon as possible to [email protected].

I’m happy to announce that I have several open PhD positions in #deeplearning for #conversationalAI, #speech technologies, and more generally #MachineLearning for #sequence processing. More information here: bit.ly/3Kfx9BX If you are interested, please apply!

Our work (Yiming Wang) about loop closures for SLAM using 3D deep descriptors in collaboration with Shandong University (山东大学 SHANDONG UNIVERSITY) has been recently published in IEEE RAL. We achieve SOTA in loop closure detection. arxiv.org/abs/2111.00440. Stay tuned for source code! DigitalIndustry-FBK

The new 3D deep descriptor GeDi improves Generalisation and Distinctive abilities of our previous DIP descriptor. Point cloud registration has never been so easy. Check out our new IEEE TPAMI paper for more details arxiv.org/abs/2105.10382 #CV #DeepLearning DigitalIndustry-FBK Fondazione Bruno Kessler - FBK

We are hiring Fondazione Bruno Kessler - FBK Computer Vision and Machine Learning R&D position. The successful candidate will be involved in the Horizon Europe projects AI-PRISM and Ferox (2022-2025). Deadline for applications: 27 June 2022. #ComputerVision #DeepLearning tinyurl.com/4cvw4ur4

Come and swing by our AutoRF poster session this afternoon, June 21, 2:30pm-5:00pm, at 136b #CVPR2026 for a chat about generalizing novel-view synthesis and implicitly parking cars. Matthias Niessner Andrea Simonelli and Reality Labs at Meta

Happy to share that both our papers, Panoptic Lifting and DiffRF have been accepted to #CVPR2023! Congratulations to all the collaborators and thanks Peter Kontschieder & Meta for hosting Norman Müller and me as interns during the summer in Zurich. Was an amazing experience 😁

Looking for 3D-consistent panoptic segmentations without the typical frame-to-frame flickering? Check out this amazing work by Yawar Siddiqui !

📢Panoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: youtu.be/QtsiL-6rSuM Yawar Siddiqui

Very excited to announce our final line-up of fantastic speakers at this year's #CVPR2025 workshop on Open-World 3D Scene Understanding with Foundation Models ✨ #OpenSUN3D #cvpr2025 📆 June 12, 2pm-6pm 🏡 opensun3d.github.io

Meet MapAnything – a transformer that directly regresses factored metric 3D scene geometry (from images, calibration, poses, or depth) in an end-to-end way. No pipelines, no extra stages. Just 3D geometry & cameras, straight from any type of input, delivering new state-of-the-art

See you later at the #iccv25 Oral Session 6B (Kalākaua Ballroom) at 1PM and poster 356 from 2:30PM! We will present our paper “Easy3D: A Simple Yet Effective Method for 3D Interactive Segmentation” with Norman Müller Project + Code: simonelli-andrea.github.io/easy3d