Xiaokang Chen

@small-beebee Hi, maybe this link could help you ~ https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch/issues/1#issuecomment-684875832

你好，我们这个项目使用的框架是做语义分割的，但是提出的算法实际上是针对RGBD数据的一种双路Backbone。如果想做目标检测的话，可以在目标检测框架中使用我们这个双路网络。

Thanks for your attention. You could get the depth map from the official disparity map (in '.png' file) and camera parameters (in '.json' file). Here we show some example code:...

@Serge-weihao In Cityscapes, we only have raw depth maps, so D == RD.

@SunXusheng5200 Hi, if you could understand Chinese, please refer to this issue: https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch/issues/2

@TXH-mercury Hi, we didn't use any algorithm to fill in the missing values.

@xiaojiangjiangjinger Sorry, we haven't planned to upload the HHA maps of Cityscapes online for the time being. Maybe you could try to convert them following https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch/issues/1#issuecomment-684875832 😄

Hi, the backbone model are all pretrained on ImageNet-1K.

Sorry for the late reply. (1) For the first question, I think the main difference between 2.5D Seg and 3D Seg is that 2.5D Seg takes 2D images as input,...

> Hello, I'm trying to study about your code. But when I analysis your code, I can't find DeepLabV3+ Decoder in your code. Could you please tell me where the...