Incorrect Visualization Results (using SMPL)

[juxuan27]

I'm very interested in this dataset so I did some experiments with SMPL backbone. But the result turns out quite surprising, so I further analyzed the dataset. My approach is to use run_vis.py to re-run unreasonable videos on my model. And here are my results:

• gBR_sFM_c09_d04_mBR4_ch07

with the setting

flags.DEFINE_string(
    'video_name',
    'gBR_sFM_c09_d04_mBR4_ch07',
    'input video name to be visualized.')
flags.DEFINE_enum(
    'mode', 'SMPL', ['2D', '3D', 'SMPL', 'SMPLMesh'],
    'visualize 3D or 2D keypoints, or SMPL joints on image plane.')

• gBR_sBM_c05_d04_mBR0_ch08

with the setting

flags.DEFINE_string(
    'video_name',
    'gBR_sBM_c05_d04_mBR0_ch08',
    'input video name to be visualized.')
flags.DEFINE_enum(
    'mode', 'SMPL', ['2D', '3D', 'SMPL', 'SMPLMesh'],
    'visualize 3D or 2D keypoints, or SMPL joints on image plane.')

• gJB_sBM_c06_d07_mJB3_ch05

with the setting

flags.DEFINE_string(
    'video_name',
    'gJB_sBM_c06_d07_mJB3_ch05',
    'input video name to be visualized.')
flags.DEFINE_enum(
    'mode', 'SMPLMesh', ['2D', '3D', 'SMPL', 'SMPLMesh'],
    'visualize 3D or 2D keypoints, or SMPL joints on image plane.')

I'm wondering if anyone else has similar results? Or did I make a mistake on the code running? Cause I found hundreds of videos like above.

[liruilong940607]

Hi Thanks for your interests in our dataset!

There are a few sequences in the dataset that are poorly reconstructed. So we provide a filter list through manual check. The three examples you posted here are all included in that filter list. Please check for the file ignore_list.txt, and the descriptions in the end of this page: https://google.github.io/aistplusplus_dataset/download.html

Thanks.

[juxuan27]

Sorry for forgetting to check the ignore_list.txt and thank you for your answering! I list some other videos as follows:

• gBR_sBM_c05_d04_mBR0_ch06

• gBR_sBM_c04_d06_mBR2_ch05

• gBR_sBM_c03_d06_mBR4_ch08