🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

BlenderProc 2.5.0 is out! Features: - segmentations now in the same rendering call - support for MatterPort3d - a Kinect depth noise model - intersecting spotlights with the camera frustum, creating hard lighting situations And much more! github.com/DLR-RM/Blender…

Our #ECCV2022 workshop on Recovering 6D Pose in Tel Aviv happens on Sunday! cmp.felk.cvut.cz/sixd/workshop_… Find great speakers and posters all around 6-DoF. Learn about brand-new performance gains in the #BOP challenge 2022 and how the #sim2real gap is vanishing.

6D Object Pose Estimation has seen huge progress in accuracy, speed and sim2real transfer. Read our analysis on the latest BOP challenge 2022 results, here:

📢 Benchmark for 6D Object Pose Estimation 📢 #BOP challenge 23 opened! bop.felk.cvut.cz/challenges/bop… Results to be presented at the #R6D workshop at #ICCV2023. The challenge has always pushed the field forward. This year: ❓unseen objects❓. Can you onboard a new object in 5mins?

The new BOP challenge 2023 pushes generalizable 6D object pose estimation. 🏆 Visit us this Sunday at the mixed reality workshop #CV4MR at #CVPR2023 🇨🇦 and learn about the current state of 6D object pose estimation and the next challenges. arxiv.org/abs/2302.13075

The 2023 BOP challenge report is out, measuring progress in 6DoF instance pose estimation: arxiv.org/abs/2403.09799 Accuracy is excellent if objects are known in advance. For unseen objects, still pretty good but slow! Middle: best method for known objects, right: unseen obj.

🚀Participate in our Open-Vocabulary 3D Scene Understanding challenge #CVPR2025 🏆Win one of two RTX 4090 ⏰ Deadline: June 14 📚Details: opensun3d.github.io 1️⃣3D Object Search opensun3d.github.io/cvpr24-challen… 2️⃣3D Functionality Grounding opensun3d.github.io/cvpr24-challen… #CVPR2024 Matterport

📈 BOP update: Deadline for the 2024 challenge is extended to November 29! BOP'24 focuses on model-free and model-based 2D/6D object detection, and introduces three new datasets from Meta and NVIDIA – HOT3D, HOPEv2, and HANDAL. bop.felk.cvut.cz/challenges/bop…

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!