具身开发者社区

外观

论文arXiv 2610.1467918 天前

HumanPhys：面向真实世界视觉推理的以人为中心的物理世界感知基准 ​

HumanPhys面向以人为中心的真实物理感知，程序化生成标签与训练语料，并在多种开闭源MLLM上验证六维能力挑战。

AI 整理
  • 本体 SDK 与控制
  • 感知与导航
  • 具身模型

原文链接：HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning（arXiv 2610.14679 · 发布日期：2026-10-10）

HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning

HumanPhys面向以人为中心的真实物理感知，程序化生成标签与训练语料，并在多种开闭源MLLM上验证六维能力挑战。

核心要点 ​

  • 现有MLLM基准与训练语料尚未联合监督这些以人为中心的物理量。
  • HumanPhys覆盖空间状态、运动学、眨眼、形变、光照和相机姿态六维感知。
  • 标签由传感器标定、源元数据或渲染器状态程序生成，而非人工或估计器生成。
  • 在多种开闭源MLLM上评测，发现六类能力对当前模型仍具挑战。

验证范围与局限：验证范围为HumanPhys基准及其真实物理感知问题、渲染探针和一系列开闭源MLLM。

英文摘要 (Abstract) ​

We introduce HumanPhys, a human-centric benchmark for real-world physical perception, and a training corpus emitted by the same pipeline. Each question targets a physically grounded quantity related to people, including depth, inter-person distance, gaze angle, displacement, velocity, heading-step trajectory, blink count, and contact-deformation strength. The rendered probes additionally test illumination inference from body and face cues and camera ego-motion, both with and without a person in the frame. All labels are derived programmatically from sensor calibration, source metadata, or renderer state, rather than written by annotators or produced by estimators on the benchmark frames. HumanPhys systematically probes six dimensions of human-centric physical perception: spatial state, kinematics, blink events, deformation, illumination, and camera pose. To the best of our knowledge, no existing MLLM benchmark-and-training corpus jointly supervises this set of human-centered physical quantities under direct metadata- or renderer-derived labels. The six dimensions appear only partially dissociable across the tested MLLMs. We benchmark a range of open- and closed-source MLLMs on HumanPhys and find that all six capability dimensions remain challenging for current models. We hope HumanPhys will support future research on multimodal systems that perceive and reason about people in the physical world.

作者：Yiming Zhang, Enzhi Zhou, Junan Lin, Dulan Zhou, Weiqiang Wang, Yuge Huang, Jian Liu

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2610.14679：HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning访问 2026-10-21