Deep Image Matting paper implementation in PyTorch.

1. "fc6" is dropped.
2. Indices pooling.

"fc6" is clumpy, over 100 millions parameters, makes the model hard to converge. I guess it is the reason why the model (paper) has to be trained stagewisely.

• The Composition-1k testing dataset.
• Evaluate with whole image.
• SAD normalized by 1000.
• Input image is normalized with mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].
• Both erode and dialte to generate trimap.

• Python 3.5.2
• PyTorch 1.1.0

Follow the instruction to contact author for the dataset.

Go to MSCOCO to download:

• 2014 Train images

Go to PASCAL VOC to download:

• VOC challenge 2008 training/validation data
• The test data for the VOC2008 challenge

Extract training images:

$ python pre_process.py

$ python train.py

If you want to visualize during training, run in your terminal:

$ tensorboard --logdir runs

1. Test:

$ python test.py

It prints out average SAD and MSE errors when finished.

1. Download the evaluation datasets: Go to the Datasets page and download the evaluation datasets. Make sure you pick the low-resolution dataset.

2. Extract evaluation images:

$ python extract.py

3. Evaluate:

$ python eval.py

Click to view whole images:

Image	Trimap1	Trimap2	Trimap3

Download pre-trained Deep Image Matting Link then run:

$ python demo.py

Image/Trimap	Output/GT	New BG/Compose

若对您有帮助可给予小小的赞助~