您的位置: 首页 > 文章 > Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss 分类: 文章 • 2024-02-14 14:33:58 Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss insights 3DIou loss Homoscedastic noise Heteroscedastic noise 3D框的representation 重要结论 distance 越远其variance越大很容易想 而对于图像中的车框,越远车框变化越小,而越近变化越大,所以variance近大远小