ECCV 2026 workshop paper improves FoundationPose by enforcing a coherent scene
ducha_aiki · x · 2026-09-09
The paper "A Simple and Effective way to Improve FoundationPose by Enforcing a Coherent Scene" is being presented at the ECCV 2026 workshop on Scalable 3D Scene Generation and Geometric Scene Understanding (poster #3), proposing a simple scene-coherence constraint to improve FoundationPose pose estimation.
More from Embodied
- Home appliance giants race to build humanoid robot butlers: LG CLOiD, Haier HIVA, Midea MIRA, Hisense Savvy — CyberRobooo · 2026-09-09
- Huawei, Xiaomi and Apple launch foldables within 72 hours; 107 'foldable concept' A-shares up 110% — alysha_lobo · 2026-09-09
- Why humanoid robots won't catch up to human workers any time soon — jjvincent · 2026-09-09
- 0.54M-parameter robot policy hits 95% on LIBERO, 7700x smaller than π0.5 — ChongZzZhang · 2026-09-09
- NVIDIA open-sources Alpamayo 2 Super autonomy model, live deep dive set for Sept 9 — PyTorch · 2026-09-09
- kornia-rs: Rust Low-Level 3D Vision Library Outperforms OpenCV and NVIDIA VPI — edgarriba · 2026-09-09