Ziyang SONG

> > > Hi @longbowzhang, thanks for your compliment! > > [1] To train PoseNet that lifts COCO defined joints, we use 2D-3D joint pairs regressed from the SMPL fits...

> > > Hi @Szy-Young, for both "pose2mesh_human36J_gt_train_human36" and "pose2mesh_human36J_train_human36", the input 2D pose and groundtruth 3D pose for PoseNet are from Human3.6M dataset annotations. > > xxJ (in your...

@Jiakui 其实不能说predict时没用到ctc...在处理DNN模型输出结果的decode函数里作者自己实现了最简单的基于Best Path Decoding的ctc解码，你会发现用英文句子做测试输出结果单词之间没有空格...

Hi @baurst, thank you for your interest! Here are some step-by-step suggestions to check the reproduction: 1. **KITTI-SF pre-processing** ``` python data_prepare/kittisf/process_kittisf.py ${KITTI_SF} ``` I've uploaded our processed data to:...

Hi @baurst , thanks for your feedback! ### 1. Experiment pipeline In your reported results, the **SF-train** and **SF-val** of **Round 2** is not needed. In round1, we train the...

Hi @amiltonwong You can use the following code for a quick visualization with Open3D: ```python # pc: (N, 3) numpy array # segm: (N,) numpy array import open3d as o3d...

Hi @wzq20030207 thx for your interest. You may refer to this discussion on [openreview](https://openreview.net/forum?id=ecNbEOOtqBU) for information about time cost. 

Hi @hualuojingye Thank you for your interest in our work! Our processing follows the label format of the SemanticKITTI dataset. You may refer to http://www.semantic-kitti.org/dataset.html for more details.