jacksyu / hoi-matting Goto Github PK

When will the dataset be released?

Dear @JackSyu
Almost 2 years pasts since your paper published. But LFM40K and UFM75K (as far as HOI Matting Slim1) are still not published.
According to instruction here i've sent you a request from university email (1.5 years ago) but had no answer.

1. Are you still accepting requests for these datasets? Can you then answer to my request?
2. Are you still going to publish LFM40K and UFM75K as mentioned in readme?

Hello, I'm interested in your research. Can you provide the source code please?

As the dataset is available upon request now, it might be a good idea to document any surprising things about it to ensure that results will be reproducible.

Training dataset (train_list.txt)

• Image 165 is in CMYK color space (4 color channels). OpenCV will load it correctly, but when using Pillow, you have to call .convert("rgb") on the image first.
• Image 66 is a duplicate of image 236.
• Image 233 is a duplicate of image 291.
• The alpha for image 235 has a different size than the image downloaded from the internet.

Test dataset (test_list.txt)

• The images 8 and 33 have a different size than the image downloaded from the internet.
• To get rid of the warning DecompressionBombWarning: Image size (100920000 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack. when using Pillow to load test image 33, you can set Image.MAX_IMAGE_PIXELS = None.

I see three options for image size the issues:

1. Resize the images (might be inaccurate)
2. Crop the images (would have to find out numbers first)
3. Skip images during training/testing. The trained model might be slightly less powerful, but it is probably not really noticeable.

I think that the third option is the easiest and therefore the best choice for reproducibility.

Hi, great work! Do you have scheduled timeline for releasing the datasets?