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
- NVIDIA releases MotionBricks: real-time humanoid motion generation at 15,000 FPS with 2ms latency — _akhaliq · 2026-10-26
- Claude Code finds root backdoor in Honda Civic head unit, then debloats it — IndraVahan · 2026-10-26
- Temple health wearable opens pre-orders, users ask: why wear it before benefits are proven — abhishekcode42 · 2026-10-26
- FLASH: GPU-native deformable sim learns cloth folding in minutes on one RTX 5090 — ChongZzZhang · 2026-10-26
- Luke Wroblewski spots it: iPhone Duo's corner radius mirrors the original iPhone — LukeW · 2026-10-26
- Humanoids shattered forecasts: half-marathon record in 2026, 100m faster than Bolt — ben_j_todd · 2026-10-26