TriWorldBench 发布：从三视角一致性评估具身世界模型
TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models
评估机器人世界模型有新工具了，TriWorldBench 用头加双腕三个摄像头同步验证预测是否一致，代码数据都开源。
TriWorldBench 是一个通过同步头、左腕、右腕三路视频来评估具身世界模型的基准。它包含 500 个 episode、覆盖 50 个双臂操作任务，使用 19 个指标衡量三视角一致性、任务对齐、物理与 3D 连贯性、运动质量、时序一致性和视觉质量。
基准用 TWB-Score 汇总整体表现，并保留单视角结果以定位预测失败的位置，将世界模型评估从单视角视觉质量扩展到跨视角一致性。
TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models
Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary views: the head view captures the overall task, while wrist views reveal local gripper-object interactions. However, evaluating these views independently cannot determine whether they describe the same action and object state. We introduce TRIWORLDBENCH, a benchmark for evaluating embodied world models through synchronized head, left-wrist, and right-wrist videos. It contains 500 episodes across 50 bimanual manipulation tasks and uses 19 metrics to assess tri-view consistency, task alignment, physical and 3D coherence, motion quality, temporal consistency, and visual quality. By combining cross-view checks with measurements tailored to each camera, the benchmark evaluates whether plausible individual videos also form a consistent prediction of the intended task. We summarize overall performance with TWB-Score and retain per-view results to identify where predictions fail. This extends world-model evaluation beyond single-view visual quality. Code, data, and metric definitions are available at https://github.com/TriWorldBench/TriWorldBench.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include TriWorldBench, world models, embodied AI, robots.
Source attribution: curated from arXiv cs.AI (@Xuanyi Liu, Haofeng Wang, Ruiqi Li, Danni Yu, Rui Wan, Ruixu Zhang, Siyu Tao, Xue Yang, Shaofeng Zhang, Zicheng Zhang, Jiaqi Zhang, Siwei Ma).
