OmniAct3D:全景3D检测框架论文发布
Get the story
2026年10月5日,arXiv Computer Vision 频道发布 OmniAct3D 论文,提出一种面向全景 3D 检测的框架。该框架将基于视觉基础模型(VFM)的透视视角 3D 检测器适配到等距柱状投影(ERP)全景输入,并引入三个模块:ERP-Ray Geometry Adapter(ERGA-Ray)、Visual-Action Reasoning Chain(VARC)与 Appearance-Guided Heading Expert(AGHE),分别处理几何适配、证据驱动推理与朝向估计。目前公开信息仅涉及论文方法概述,尚无实验结果或第三方验证报道。
Generated from reports · updated 16 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Computer VisionOmniAct3D:用基础几何与证据驱动推理做全景 3D 检测
OmniAct3D 把基于视觉基础模型(VFM)的透视视角 3D 检测器适配到等距柱状投影(ERP)全景输入,提出 ERP-Ray Geometry Adapter(ERGA-Ray)、Visual-Action Reasoning Chain(VARC)与 Appearance-Guided Heading Expert(AGHE)三个模块。
Heat trend
Current heat 6·Comparable peak 10(Oct 5)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.