search

zhixuany / HUMBI

This repository contains official code (in MATLAB) for exploring and visualizing HUMBI dataset introduced in the paper "HUMBI: A Large Multiview Dataset of Human Body Expressions" (CVPR 2020).
MIT License
117 stars 8 forks source link

reconstructed SMPL pose is inconsistent with the image #14

Closed GentleDell closed 4 years ago

GentleDell commented 4 years ago

Thank you very much for the wonderful work and for releasing this dataset.

I am able to run the python "hello_smpl_for_humbi.py" script on the Sample_body data, but the mesh generated by the python script is inconsistent with the images in /subject_1/body/00000017/image (e.g. /image0000032.jpg). E.g.

The image from the sample data: rsz_image0000000

Reconstructed mesh generated by the python scripty: rsz_screenshot_from_2020-10-12_15-49-08

In the image, the left and right palms face each other. However, in the reconstructed mesh, the palms face outside.

I was wondering whether I use the python script correctly and if you observed this as well.

Below are my configurations: SMPL model: I use the model provided in this repo at HUMBI/body/model/basicModel_neutral_lbs_10_207_0_v1.0.0.pkl. SMPL codes: I use the codes from the SMPL website and I have tried with both ver1.1 and ver1.0 but the above inconsistency still exists. Configuration of the "hello_smpl_for_humbi.py": dataset_path = './Sample_body'; subject = 1 frame = 17 outmesh_path = './smpl_mesh.obj' model_path = './body/model/basicModel_neutral_lbs_10_207_0_v1.0.0.pkl'

Thank you very for your time and your help would be much appreciated. Best

Update: I try the python script with subject_88 (subject_88/body/00000025/image) and the pose of the reconstructed hands is not consistent with the image too.

Xbbei commented 3 years ago

@GentleDell Hi, Recently, I want to use this datasets, but i meet the same problem with you, so did you solve this problem?

Best wishes!

GentleDell commented 3 years ago

@Xbbei

Hello Xbbei,

No, I made the decision not to use this dataset. Because there are many similar cases like this in the dataset. But maybe you can try to simply rotate the poses of the hands.

Best,

Xbbei commented 3 years ago

@GentleDell Hi, GentleDell,

Thanks for your reply! Can you tell me which datasets you use?

Thanks Best wishes!

GentleDell commented 3 years ago

Hi,

Depending on the tasks you are going to do, you might be interested in VIBE, GraphCMR, RotationContinuity, TexturePose, MultiGarmentNetwork.

I would recommend you read related papers published in recent conferences to see if there are new datasets released/available.

Best,