arXiv preprint / 6D位姿

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

作者：Yipu Zhang, Jintao Cheng, Weilun Feng, Jiehao Luo Chuanguang Yang, Zhulin An, Yongjun Xu, Computer Engineering, Engineering · 单位：Department of Electronic and Computer Engineering, HKUST, State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, School of Data Science and Engineering, South China Normal University, Xiamen Institute of Data Intelligence · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2026-05-15

6D位姿估计
新标签打开 AlphaXiv新标签打开 Code
Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer figure
AlphaXiv 中文概览（可滚动查看）