search

fnzhan / UNITE

[CVPR 2022 Oral] Marginal Correspondence for Conditional Image Generation, [CVPR 2021] Unbalanced Feature Transport for Exemplar-based Image Translation
192 stars 26 forks source link

Queries #5

Open abhigoku10 opened 2 years ago

abhigoku10 commented 2 years ago

@fnzhan hi thanks for open-sourcing the code base , its really great work i have few queries

  1. can we train the code for other semantic datasets like bdd100k / cityscapes? if so what changes have to be made
  2. can we train the code for custom fashion dataset for region wise dressing ? if so what is the procedure

Thanks in advance

fnzhan commented 2 years ago

Hi,

  1. of course, the model can be applied to other datasets. You should add the python file of the corresponding dataset, e.g., data/ade20k_dataset.py, and modify the processing code here https://github.com/fnzhan/UNITE/blob/d84b833c7840b5aa27596fa1ea0e4e98f576944b/models/pix2pix_model.py#L149

  2. The model can work if a semantic correspondence can be built. Thus, if the region is annotated with semantic segmentation, the model can be applied by following similar procedure with ADE20K.