ECCV 2026 workshop launches BOP-Refer, a benchmark for language-grounded 3D object localization
ducha_aiki · x · 2026-09-08
The 11th Workshop on Recovering 6D Object Pose (R6D) at ECCV 2026 (September 8, Malmö) will present the BOP Challenge 2026 and a new benchmark, BOP-Refer: given an input image with known intrinsics and a natural-language referring expression (e.g. "the tool for watering plants"), models must localize the object in 3D or 2D, putting VLM grounding under concrete evaluation.
- Invited talks: Ranjay Krishna (revisiting grounding), Bernadette Bucher (how much pose a robot needs in mobile manipulation), Sergey Zakharov (synthetic worlds for scalable robot learning), and Intrinsic's AI for Industry Challenge
- Speakers span University of Washington, University of Michigan, Toyota Research Institute, Google, and Intrinsic
- Accepted workshop papers are already public; a poster session follows the challenge presentation
More from Embodied
- Tesla Cybercab's impressive maneuver sparks praise: a human driver would have crashed — XFreeze · 2026-09-08
- Roboticist's field notes: LLMs handle grasping, but collision avoidance and dexterity remain hard — YiMaTweets · 2026-09-08
- China's self-driving electric trucks now log 1M+ km daily, reshaping freight — aitrendz_xyz · 2026-09-08
- RoboDK CAM turns toolpaths into robot instructions for machining, polishing and more — lukas_m_ziegler · 2026-09-08
- EmbodiedSkills: A Unified Framework for Orchestrating VLA Robot Agents — Wei Wang · 2026-09-08
- Dev Builds a TikTok-Style Mobile UI for 15+ Years of Replication Archives — Josikinz · 2026-09-08