yankai

Thanks for your great work. And i want to repeated your classic benchmark bridge model pcd，but I can't find it. Would you help me, where can i download the bridge...

Thanks for sharing great work. I can build midas cpp ros,but when runtime,no error happened,but can't get correct result. Would you check ros cpp code,it's sure there are some bugs,...

大佬们，想问下，如何变为自己相机分辨率的识别检测呢，微信18811720989欢迎交朋友，希望得到支持，感谢～

Hello,thanks for great work. But i wander what camera model you are used for fisheye model ,It's opencv fisheye KB model or ocam model? Your background pdf doc present the...

标定方法和数据集

8

大佬您好，想问下，标定的时候需要相机不动，转动棋盘格是吗，我看到，你的程序里每个相机标定数据是cam-x单独的，想问下，程序先单目后多目标定，多目标定的数据集用的是各个单目的数据集吗，多目数据不需要同一个棋盘格同时出现在多个摄像头里面吗？谢谢大佬，另外，数据集可否发一份呢？ 我的qq邮箱为[email protected]；微信为18811720989。期待认识大佬~

tensorrt c++ And mask decoder can be fp16 without too big error?

2

Hello, Thank you for sharing the great work. Do you have a plan for tensorrt c++ version? That will be awsome too,Thank you very much. I see mask decoder used...

image encoder image size is too big ,can reduce 1024 to 640/480 for acceleration?

3

image encoder image size is too big ,can reduce 1024 to 640/480 for acceleration?