search

YuliangXiu / ECON

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration
https://xiuyuliang.cn/econ
Other
1.08k stars 106 forks source link

the results of using infer.py is different from using benchmark.py #66

Closed Holmes-Alan closed 1 year ago

Holmes-Alan commented 1 year ago

For the same example from CAPE dataset, using infer.py code gets different 3D results to benchmark.py. Could you please tell me what the problem is? Picture1

YuliangXiu commented 1 year ago

benchmark.py uses gt SMPL as 3D body prior, while infer.py uses SMPL-X predicted by PIXIE instead.