Fabien Baradel

Hi @haiphamcse, that's a good question. We use the 6FPS variant which already leads to 286'228 images.

You are welcome. That's a good question. We will provide PCOD on 3DPW and AGORA in an updated version of our paper on arXiv. Thanks for pointing this out. We...

Hi @haiphamcse , we do not plan to release the evaluation code for the moment. It is possible that you get bad performance because you do not give the ground-truth...

Hi, since Multi-HMR is taking as input the entire image you do not need to use the GT primary keypoints compared to single-erson methods. Just feed the image to Multi-HMR...

Good question @nguyenquivinhquang indeed we followed this strategy. At inference time, we use the regressor from from [BEDLAM](https://github.com/pixelite1201/BEDLAM/blob/ebf8bb14a43de46cc74dca4c00c13e571b325726/train/dataset/dataset_smpl.py#L84) to regress the SMPL vertices from the SMPL-X mesh. Please have a...

Hi @nguyenquivinhquang , yes we followed this evaluation protocol for CMU Panoptic similar to what ROMP/BEV are doing. I think that this way of taking missing detection into account comes...

Hi @nguyenquivinhquang , thanks for sharing the table. Please take into account that results in the paper are obtained after fine-tuning on the 3DPW training data. The first line that...

Hi @nguyenquivinhquang @haiphamcse , I just want to let you know that today we are releasing the training and evaluation code of Multi-HMR 😄 We are providing the training code...

Thank you @nguyenquivinhquang 😃

Hi @nguyenquivinhquang , we do not plan to release the dataloader for MuPoTS and CMU for the moment, maybe in a near future. I will let you know. Which joints...