ECCV Paper Introduces 360CityArena: A Realistic Urban Navigation Benchmark

CSProfKGD · x · 2026-08-13

Researchers have introduced 360CityArena for ECCV 2026, a realistic urban navigation benchmark built from 360° videos of Akihabara, Tokyo. It aims to evaluate whether embodied AI agents can understand, navigate, and reason about real-world urban environments.

The benchmark includes 602 real-world videos covering 85 streets, featuring 175 navigation and spatial reasoning tasks. The results highlight a massive gap between current AI and human capabilities: while humans achieved a 77.3% success rate, the best LMM-based agent scored only 17.1%. The entire environment and all tasks are fully open-sourced.

Related event: HAL-UTokyo Releases 360CityArena City-Level Navigation Benchmark(2 posts)→

Original post →

More from Embodied

Embodied channel →