Faster and More Accurate Pose Estimation of Unseen Objects! MatchU @ #CVPR2024 provides a fuse-describe-match framework that fuses cross-modal data by combining geometry and image features of objects never seen before. CVPR 2024, Seattle Thu 20 June | 10:30 | Session 3 | #42

Super happy to see my name on that list 🤩✨ Congrats to all #CVPR2024 Outstanding Reviewers! Looking forward to seeing you in Seattle next week.

Looking for data to evaluate your pose estimation or object grasping pipeline? HouseCat6D #CVPR2024 Highlight: sites.google.com/view/housecat6d 160K Poses, 10M Grasps, 41 Scenes, 194 Objects, 10 Household Categories, 3 Modalities CVPR 2024, Seattle Fri 21 June | 10:30 | Session 5 | #283

Got unfortunate news from #ECCV2024 (and waited too long to load the paper id list)? Consider sending the (slightly revised) version of your paper including the reviews to the GCPR fast track and present in Munich in September already!

The complete GCPR-VMV program is now online and it is still not too late to join us! We have tutorials on Virtual Humans, Quantum-Enhanced Vision and 3D Shape Analysis, as well as four keynote talks, four PI-Talks and three research spotlights from junior researchers.

Having a great time at #GCPR-VMV 2024! Thanks everyone for joining the tutorial and the interesting questions :)

Zorah Lähner speaking about challenges and future directions in 3D shape analysis. Exciting discussions on the first day of #gcpr #vmv in Munich.

Congratulations to all awardees for their great contributions to the research community of #gcpr #vmv @ GCPR-VMV-2024 in Munich. Congrats namely to Lukas Kirchdorfer, Francesco Croce, Angela Dai, Justus Thies!

Christian Theobalt talking about Neural Models of the Real World at #gcpr #vmv 2024 in Munich

Fulfilling my academic duties as a conference chair!!! O'Zapft is 🍺🍻 🍺 #GCPR #VMV

Thanks for inspiring great discussions with the keynote talks from Torsten Möller and Serge Belongie and industrial insights from our gold sponsor ZEISS on Thursday at #gcpr #vmv 2024 in Munich.

Amazing line-up of input talks on the last day of GCPR-VMV 2024. Thanks for the insightful input Tatiana von Landesberger, Cordelia Schmid, Jörg Stückler and all the authors that presented at #gcpr #vmv 2024 in Munich!

A great week at #gcpr #vmv 2024 in Munich has come to an end. Congrats to all the paper awardees announced in the final session and thanks to all attendees for an amazing conference! See you 2025 in Freiburg / Erlangen.

Not long until the 9th(!) Workshop on Recovering 6D Object Pose (R6D) at #ECCV2024, Sunday AM. Great speakers, and vannguyen, Tomáš Hodaň and Martin Sundermeyer will tell us about the #BOP Challenge 24 - the challenge is still running, but you get to see early bird results!

🚀 Check out our latest work on object pose estimation which we present at #ECCV2024 in Milan! 📷 Alignist predicts pose distributions from a single image and a 3D CAD model. Geometry and correspondence predictions are combined: 📌arxiv.org/abs/2409.06683

🚀 Want to distribute information over a scene graph with generative diffusion? Check out EchoScenes at #ECCV2024 in Milan. Poster #309, Thu 3 Oct 10:30am. 📷 EchoScenes communicates graph node states over edges exemplified with 3D scene generation: 📌sites.google.com/view/echoscene

It's been an amazing week at #ECCV2024 in Milano. Big shout-out to the entire organization committee for making this fabulous event happen! Thanks for providing a great space to discuss computer vision research with old and new friends and colleagues!

🚨 Call for Participation — TRICKY @ ICCV 2025 🌺 Join our challenges on monocular depth & category-level pose for transparent/specular objects! 🧊💎 📅 Challenges: June 📄 Paper due: July 4 🔗 sites.google.com/view/iccv25tri… #ICCV2025 #3DV #AI #CV #TRICKYchallenge

🎯 Presenting at #CVPR2025 today! 📍 Poster #341 | Hall D | 17:00–19:00 MM-OR: A large multimodal dataset for understanding complex surgical scenes 🏥🤖 RGB-D, audio, robot logs & more 🔗 github.com/egeozsoy/MM-OR w/ Özsoy, Pellegrini, Czempiel, Busam et al. #ComputerVision #OR

🚀 GCE-Pose today at #CVPR2025! 📍 16:00–18:00 | Exhibit Hall D | Poster #96 Category-level object pose under occlusion via 🔹 Semantic Shape Reconstruction 🔹 Global Context Enhancement 🔗 colin-de.github.io/GCE-Pose 👥 Li, Xu, Huang, Jung, Yu, Navab, Busam #3DVision #RGBD #GCEPose