coco

> i'm having my own unrelated issues, but if i were to take a guess, maybe make the origin focused on [a point of infinity](https://www.flickr.com/photos/polarstar/14085294791/) Nice idea! I read (not...

> @Borailuce99 Can you please check this error and guide what I am missing here, While executing the "360 inward facing scene" I get this error: > > Aspect ratio...

> This is usually due to a mismatch in the version of pytorch which pytorch3d was built with and the version of pytorch which you have at runtime. How did...

> > This is usually due to a mismatch in the version of pytorch which pytorch3d was built with and the version of pytorch which you have at runtime. How...

> I’m not sure what do you mean… I'm wondering how to get the canonical human

> 我还是不明白您的问题是什么意思？ 就是我想请教一下，如何用图像上2d的人物生成paper中“大”字形的3d人体模型？是通过SMPL拟合得到参数后，调节姿态参数得出来的吗？

ROMP建立起人体的mesh模型，这个过程都是靠图像中的2d人物吧？我不太明白既然有了可编辑的mesh，大字型和T字型为什么效果会有所不同呢？感觉只是手动调整了可视化的结果，都是表示同一个mesh；顺便再问一问怎么让人体做出自己想要的动作呢？难道是人为控制pose的参数吗？还是说从其他的视频里面通过某种方式提取出动作信息，来控制这里的人体？

SMPL的mesh可以带颜色吗？还是通过其他什么方式给mesh上色？

 What are necessary for training command like this: ``` python train.py --scene_dir ./data/bike --name=bike_human --load_background=bike_background --train_mode=smpl_and_offset ```

> Hi, > > Can you get the strictly same results when evaluate twice on your machine? Yes, I run the command twice with same setting, and get same results.