Yu Sun

Results 301 comments of Yu Sun

Thanks for your reminding. The training code is released to re-implement our ICCV paper. In the latest ICCV paper, we have dropped the usage of redundant datasets for comparison. But...

1. The "SMPL param gts" come from Human3.6M. MPI-INF-3DHP doesn't have the SMPL parameters provided. 2. The evaluation protocol 1 (Tab. 1) uses the entire 3DPW dataset. 3. ROMP takes...

Hi, Tiange, Thank you for your concern BMP claims that they follow the evaluation protocol of VIBE on 3DPW. But all results on Tab. 5 they reported are so weird....

Hi, Diyu, Thanks for pointing out this! Honestly, I didn't mean to, but this mistake might be helpful to infer the 'invisible' part of the body. I am not sure...

@RedOrient 是的,1评估用的ground truth label和评测代码与2/3都不一样。

This bug may caused by wrong dataset sampling ratio. For instance, if you add / remove the 'dataset' used for training at [here](https://github.com/Arthur151/ROMP/blob/abe6c5adfb4cfe262e3eea71678166b11e091262/configs/v1.yml#L4). Then you should also change the sampling...

请确认一下图片的读取路径是不是对的,我默认是将所有的数据集都放在一个名字叫dataset的文件夹里的, 通过设置 [这行](https://github.com/Arthur151/ROMP/blob/abe6c5adfb4cfe262e3eea71678166b11e091262/romp/lib/config.py#L142),可以改变数据集的位置,对于每个数据集的位置,例如h36m可以修改[这行](https://github.com/Arthur151/ROMP/blob/abe6c5adfb4cfe262e3eea71678166b11e091262/romp/lib/dataset/h36m.py#L12)

这个bug还是比较容易的,你打印一下imgpath不就知道为什么读取不到图片了么

奇怪了,你这不是最新版的代码吧,77行不是已经把图片地址加进去了么。 Anyway, good for you.

客气了,有问题再找我。有售后的,觉得好再来~