sam_inversion icon indicating copy to clipboard operation
sam_inversion copied to clipboard

[CVPR 2022] GAN inversion and editing with spatially-adaptive multiple latent layers

Results 10 sam_inversion issues
Sort by recently updated
recently updated
newest added

The direction `csc_glasses_remove.npy` is same as `csc_glasses_add.npy`, while it should be the opposite of `csc_glasses_add.npy`.

Hey @GaParmar and @junyanz ! 👋 Good work on this project I was very impressed by the reconstruction quality of the suggested inversion process. The images actually look better that...

Hi, I think the filename for "cats" is wrong here: https://github.com/adobe-research/sam_inversion/blob/4852a2a033ac5af981f91b9eb2baa3df6e2229fa/src/sam_inv_optimization.py#L117 Since there is only "e4e_cats.pt" in https://www.cs.cmu.edu/~SAMInversion/ckpt/ But I think this one is bad too as I'm not able...

Thanks for the article! For example, how can I manipulate only the pose of a car?

I'm running `python src/sam_inv_optimization.py --image_category "cars" --image_path car1.jpg --output_path "output/cars/" --sweep_thresholds --generate_edits` where car1.jpg is a 1200x800 rgb image. I get the following errors: ```Traceback (most recent call last): File...

Please provide the segmenter_utils.py file

Hi, I am not sure this code for optimization based model is good... Because it is not similar to inverted face img to source img. And I am wondering if...

Thank you for your great work! Is there any plan to release datasets or inversion results by single latent spaces?

Thanks for your work! I'm wondering will the encoder weight be released later.