R2ET icon indicating copy to clipboard operation
R2ET copied to clipboard

(CVPR 2023) Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry

Results 10 R2ET issues
Sort by recently updated
recently updated
newest added

Hi, can you please describe the inference config file. ``` phase: test num_joint: 22 weights: ./pretrain/shape_aware.pt device: [0] save_path: ./save/inference/ k: 0.8 load_inp_data: inp_shape_path: ./datasets/mixamo/test_shape/Ortiz.npz tgt_shape_path: ./datasets/mixamo/test_shape/Sporty_Granny.npz stats_path: ./datasets/mixamo/stats inp_bvh_path:...

采用smpl格式的动作进行retargeting时,应该如何对输入的smpl格式的动作进行处理?输入smpl格式的动作进行retargeting后会有非常强烈的抖动是为什么?

Based on the way that for-loops handle the creation of the data in `extract_shape.py` (basically rewriting existing variables at each frame), I suspected that only the last mesh was taken...

hi, I use your visualize command but failed: ![image](https://github.com/Kebii/R2ET/assets/42883258/b18b40d5-578c-44ff-9036-593cefaf23c0) if I use blender itself, it also says : Failed to open dir (No such file or directory): /run/user/1008/gvfs/ ![image](https://github.com/Kebii/R2ET/assets/42883258/b8e8d131-6b6b-41eb-b834-ba91be8918d8) why...

Hi, thanks for your great work. But I have a question when I try on my own dataset. In your inference_bvh_cfg.yaml, we should input the path of both the bvh...

Is this possible to retarget the animal motions? Thank you

I followed the README instructions to do inference by running the command: ``` python3 inference_bvh.py --config ./config/inference_bvh_cfg.yaml ``` However, the output I obtained was quite jittery, unlike the smooth motion...

Hi can you please add a license to this repository

作者你好,感谢开源了这么优秀的项目,我有两个问题想请教下: 1. 论文中提到的若干评测方法,如定性结果中的∆D,定量结果中的MSE,穿模率,自接触,有实现的代码吗 2. 指标评估中Copy和Copy†的区别是什么呢,前者是根据均值方差做了归一化吗