Save the dates! 🗓️ Paper submission site (on OpenReview) is now open! openreview.net/group?id=3DV/2… #3DV2024

Super happy to announce that our work “OpenMask3D: Open-Vocabulary 3D Instance Segmentation” has been accepted at #NeurIPS2023! 🎷🎶 Project page: openmask3d.github.io Stay tuned for camera ready version and code! Ayça Takmaz Francis Engelmann Federico Tombari Marc Pollefeys NeurIPS Conference

Volumetric Semantically Consistent 3D Panoptic Mapping Yang Miao, Iro Armeni, Marc Pollefeys , Baráth Dániel tl;dr: panoptic prediction confidence+semantically consistent superpoints+graph-optimized semantic labeling and instance refinement arxiv.org/pdf/2309.14737…

I would like to thank our amazing co-authors: Xin Wang, Mahdi Rad, Bowen Pan, Ishani Chakraborty, @seanandrist, danbohus, Ashley Feniello, Bugra Tekin, Felipe Vieira Frujeri, Neel Joshi, and Marc Pollefeys! I look forward to chatting with you soon!

Handbook on Leveraging Lines for Two-View Relative Pose Estimation Petr Hruby, Shaohui Liu, Rémi Pautrat, Marc Pollefeys , Baráth Dániel tl;dr: using lines for camera pose: good ways are better than 5PC, worst - worse. arxiv.org/abs/2309.16040…

Guiding Local Feature Matching with Surface Curvature Shuzhe Wang, Juho Kannala, Marc Pollefeys Baráth Dániel tl;dr: fit ellipsoid into monodepth, require curvature consistency, better matching. No #IMC eval. #ICCV2023 openaccess.thecvf.com/content/ICCV20…

🚀Curious about the future of image matching? Today at 10:30 we are presenting GlueStick a joint deep matcher for points and lines in #ICCV2025! Come by poster 021 in Foyer Sud and chat with Rémi Pautrar, me, Yifan Yu, Marc Pollefeys, and Viktor Larsson 😃

Joint work by: Denys Rozumnyi Jiri Matas Marc Pollefeys Vittorio Ferrari Martin Oswald Code: github.com/rozumden/track…

Joint work by Yiming Zhao, Denys Rozumnyi, Jie Song, Otmar Hilliges Marc Pollefeys Martin Oswald

HoloAssist is a new multimodal dataset consisting of 166 hours of interactive task executions with 222 participants. Discover how it offers invaluable data to advance the capabilities of next-gen AI copilots for real-world tasks: msft.it/60139Uv4d

I am excited to announce our HoloAssist work at #ICCV! Get your hands on the dataset at holoassist.github.io, released under a permissive license. Meet my collaborator @big_stamp at the poster session this Friday from 02:30-04:30 PM. Huge thanks to the coauthors and

Join us today #ICCV2025 at the Google AI booth for a live demo of OpenMask3D 🛋️ (un petit amuse-bouche of our NeurIPS Conference '23 work on open-set 3D instance segmentation) ⏲️15:30 🏠Google Booth openmask3d.github.io Amazing work w/ Ayça Takmaz Elisabetta Fedele Marc Pollefeys Federico Tombari

Today Ayça Takmaz and I will present our paper OpenMask3D at NeurIPS Conference 🎷🚀 Come by to learn more about the project or to chat about related topics! 📍 Great Hall & Hall B1+B2 (level 1) #906 🕰️ 10:45-12:45 🌎 openmask3d.github.io Francis Engelmann Federico Tombari Marc Pollefeys

Today Elisabetta Fedele and I will present our work OpenMask3D at NeurIPS Conference 🎷 Visit our poster to learn more about OpenMask3D or to chat with us! 📍 Great Hall & Hall B1+B2 (level 1) #906 🕰️ 10:45-12:45 🌎 openmask3d.github.io Francis Engelmann Federico Tombari Marc Pollefeys

For #NeurIPS2023 we're presenting our latest work SNAP - Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding Geo data at scale + self-supervision = 💥 Video: youtu.be/xogrwdgNQdo Paper: arxiv.org/pdf/2306.05407 Code: github.com/google-researc… summary🧵⬇️

📢 Today, we release LabelMaker, a fully automatic tool to create semantic annotations for indoor scenes. LabelMaker will be presented as spotlight at #3DV2024 in March. 🔗 labelmaker.org 🛠️ github.com/cvg/LabelMaker with Hermann Blum , Francis Engelmann , and Marc Pollefeys

I am overjoyed to announce I am hosting the "Workshop on Urban Scene Modeling" along with an amazing team at #CVPR2025 2024! Submission deadline March 24 usm3d.github.io more two challenges, brand new dataset, and amazing keynote speakers soon...! #CVPR2024 #usm3d

Yuedong Donny Y. Chen just gave a fantastic Oral presentation of MVSplat at #ECCV2024! Come to our poster 157 to discuss more!

You're in Zurich or its zone of influence (Lausanne, Paris, BXL, Munich, London, ...) and like AI + Robots? We (@openai) together with mimic, lokirobotics, and Zurich Builds are organizing a hackathon from Fri 9 May afternoon to Sun 11. Limited spots, more below:

Multi-View 3D Point Tracking Frano Rajič, Haofei Xu, Marko Mihajlovic, Ethan (Siyuan) Li, Irem Demir, Emircan Gündoğdu, Lei Ke, Sergey Prokudin, Marc Pollefeys, Siyu Tang @VLG-ETHZ tl;dr: per-view features+depth maps->fused 3D feature point cloud->kNN-based correlation->spatiotemporal