Yuan Liu

Results 240 comments of Yuan Liu

The network parts indeed do not contain complex or advanced operations and may be able to transfer to an onnx model. However, I may not have time to support these...

Hi, it seems your model is not downloaded completedly. You may download it again. https://stackoverflow.com/questions/71617570/pytorchstreamreader-failed-reading-zip-archive-failed-finding-central-directory

Hi, do you mean that you wanna train the Gen6D on your dataset? In this case, you may follow https://github.com/liuyuan-pal/Gen6D#training and the training is relatively complex because it contains three...

You only need to finetune it on your own datasets but not these provided datasets.

The 3x4 matrix is [R;t], where x_camera = R @ x_world + t. x_world and x_camera have the shape of [3,1] as a column vector.

因为这里的bbox大小指的是正好包围这个物体的外包球的bounding box,我们可以通过bbox大小来确定物体的远近,近大远小。这里可以参考论文的补充材料的第一节。

这个我只是在里面插入了语句测了一下时间,没有具体的脚本。

Hi, I use blender to render the object. You just export the poses and render the object in blender with the pose and then composite the rendered object with the...