SMALify
SMALify copied to clipboard
benjiebob
fine-tune 3D smal fiting
Hi, @benjiebob ,thanks for your sharing.
I have tried to utilize the project to get a fine-tune smal parameters for a specific cat with a cat .obj file.
And the smal results as followed.
1.family_0.obj fine-turn to family 0 smal base model stage 0 result
2.family_0.obj fine-turn to family 0 smal base model stage 2 result
3.family_4.obj fine-turn to family 0 smal base model stage 0 result
4.family_4.obj fine-turn to family 0 smal base model stage 2 result
Seems that it can work better for cross species other in the same species with minor difference. Any suggestion for a better inner-species fine-turn result? We may Take the family_0.obj exported from data_000781_4_all.pkl as a benchmark.
Configaration for the result above: My training config use the fitter_3d/example_cfg.yaml (family_id=0) and my input .obj was exported from my_smpl_data_00781_4_all.pkl.
Hi, @benjiebob ,thanks for your sharing. I have tried to utilize the project to get a fine-tune smal parameters for a specific cat with a cat .obj file. And the smal results as followed. 1.family_0.obj fine-turn to family 0 smal base model stage 0 result
2.family_0.obj fine-turn to family 0 smal base model stage 2 result
3.family_4.obj fine-turn to family 0 smal base model stage 0 result
4.family_4.obj fine-turn to family 0 smal base model stage 2 result
Seems that it can work better for cross species other in the same species with minor difference. Any suggestion for a better inner-species fine-turn result? We may Take the family_0.obj exported from data_000781_4_all.pkl as a benchmark.
Configaration for the result above: My training config use the fitter_3d/example_cfg.yaml (family_id=0) and my input .obj was exported from my_smpl_data_00781_4_all.pkl.
Hi, have you figured out this problem?
