ROMP
ROMP copied to clipboard
Arthur151
Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]
I have.. ## Some dependency questions 1. [For CPU rendering you recommend to use the `--onnx` parameter](https://github.com/Arthur151/ROMP/blob/master/simple_romp/README.md#usage), wich [installs `onnxruntime`](https://github.com/Arthur151/ROMP/blob/bafc86897c387caae125e7119b31dc30ee317bf0/simple_romp/romp/main.py#L82). Why you not also recommend this [for GPU rendering with...
作者大大你好 I have a question about the training codes. I have read through the codes and I couldn't find the methods of Gaussion kernel size and CAR calculation used for...
您好，我使用旧版代码是可以正常训练的，但是使用最新代码就会有问题 config如下： [v1.yml.txt](https://github.com/Arthur151/ROMP/files/9142892/v1.yml.txt) 错误日志如下： ``` INFO:root:Training all layers. Traceback (most recent call last): File "D:\Software\AnacondaP\Install\envs\ROMP\lib\runpy.py", line 197, in _run_module_as_main return _run_code(code, main_globals, None, File "D:\Software\AnacondaP\Install\envs\ROMP\lib\runpy.py", line 87, in _run_code exec(code,...
您好，我在做遮挡评估的时候遇到了一些问题 前提：我的模型加入了3dpw-train set训练而成 我评估了我训练的模型结果如下： ``` DONE (t=0.22s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.267 Average Precision (AP) @[ IoU=0.50 | area= all |...
在之前一个版本的数据集代码中多数数据集有： kp3ds -= root_trans[:,None] 就是所有的3d的坐标标签都是减去根节点之后的坐标。 这样处理的话，模型预测的坐标是否就不是世界坐标系下的坐标了，而是以根节点（左、右臀中点）为零点的坐标？ 最新版本的数据集是不是因为这个原因，把root_trans也传入了模型？
I'm using bev to infer a video. After adding -t -sc 5.0 when inferring a video, I got some models at the far end shifting randomly. Is it likely causing...
Hi Yu, we used your work to extract 3D motion from 2D videos. In general, it works quite well for single-person scenarios. Nice work! However, when I tried with multiperson...
Hi Yu, thanks for your work and such an organized repo! I'm now using ROMP to get SMPL poses and would like to visualize the meshes via a perspective camera....
### Question for dataset checking Hi, Doc. Sun. After evaluation on BEV, now I want to train a model by myself from scratch. But when I run ` python -m...
No such file or directory mpi_inf_3dhp/S1/Seq1/annot.mat mpi_inf_3dhp in google drive has only annots.npz How can i find annot.mat file ?? @Arthur151
