Droliven
Droliven
Thanks for your great contributions! I want to know how to make annotation files, in other words, given a RGB image, how to get the person's uvd_29, xyz_24, xyz_17 coordinates,...
示例demo文章顶部的图片无法加载,另外,能不能将将顶部图片设置为通过图床链接加载的方式,这样速度更快些
Does this simulator directly simulatethe 3D model ? How could I get the raw imgs with distortion from two global cameras? On this basis, I want to study distortion correction...
I need to know how to use this simulator, such as how to capture and save the images in the football game, so as to design and study the football...
建议 url 格式: https://vivi98.top/印章/白云莫闲/bymx-circular.jpg 目前 url 格式: https://vivi98.top/%E5%8D%B0%E7%AB%A0/%E7%99%BD%E4%BA%91%E8%8E%AB%E9%97%B2/bymx-circular.jpg 中文建议原文显示
In your line 20 of the train.py joint_loss, it writes: parts_idx = [(np.array(p) * 3).tolist() + (np.array(p) * 3 + 1).tolist() + (np.array(p) * 3 + 2).tolist() for p in...
You said "Since Voxceleb2 official videos are of low resolution, we redownload the original YouTube videos and re-crop the videos" in the paper, but where is the youtube link of...
After restoring your pretrained model and setting the random seed, I calculate the 3D coordinate error between y_t_xyz and y_p_xyz using the following L2-norm,  ``` def xyz_error(gt, out): '''...
when running df = append_treasury(df), the error occurs
It seems that there is no "ms_deform_attn_forward" in "_C"