Yisheng (Ethan) He

抱歉，我们没有尝试过把模型转换成onnx，最远点采样部分你可以找找pointnet++有没有onnx版本可以借鉴，那个操作主要是pointnet++在用。如果有什么进展也欢迎在这个issue里和大家分享。

We use preprocessing code from PVNet to transform the pose parameter ([pvnet_code](https://github.com/zju3dv/pvnet/blob/48e5066668f7563434373bc909b842a7bd94b7b9/lib/utils/data_utils.py#L539)) and then use similar scripts as in our datasets/linemod/linemod_dataset.py to generate input to our model.

No, both the linemod and occ_linemod use 'linemod' K, the 'blender' K is only used for the synthetic dataset.

You can check if the pose is correct by transforming the object vertexes or the selected keypoint by the pose parameters and project them back to the RGB image for...

Yes, it's possible. You can modify the dataset preprocess scripts, ```datasets/ycb/ycb_dataset.py``` or ```datasets/linemod/lm_dataset.py``` to preprocess your own RGBD images and then fed them into the ```demo.py``` script to get the...