Add support for ViTMatte models

[xenova]

Usage

Example: Perform image matting with a VitMatteForImageMatting model.

import { AutoProcessor, VitMatteForImageMatting, RawImage } from '@xenova/transformers';

// Load processor and model
const processor = await AutoProcessor.from_pretrained('Xenova/vitmatte-small-distinctions-646');
const model = await VitMatteForImageMatting.from_pretrained('Xenova/vitmatte-small-distinctions-646');

// Load image and trimap
const image = await RawImage.fromURL('https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/vitmatte_image.png');
const trimap = await RawImage.fromURL('https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/vitmatte_trimap.png');

// Prepare image + trimap for the model
const inputs = await processor(image, trimap);

// Predict alpha matte
const { alphas } = await model(inputs);
// Tensor {
//   dims: [ 1, 1, 640, 960 ],
//   type: 'float32',
//   size: 614400,
//   data: Float32Array(614400) [ 0.9894027709960938, 0.9970508813858032, ... ]
// }

You can visualize the alpha matte as follows:

import { Tensor, cat } from '@xenova/transformers';

// Visualize predicted alpha matte
const imageTensor = new Tensor(
  'uint8',
  new Uint8Array(image.data),
  [image.height, image.width, image.channels]
).transpose(2, 0, 1);

// Convert float (0-1) alpha matte to uint8 (0-255)
const alphaChannel = alphas
  .squeeze(0)
  .mul_(255)
  .clamp_(0, 255)
  .round_()
  .to('uint8');

// Concatenate original image with predicted alpha
const imageData = cat([imageTensor, alphaChannel], 0);

// Save output image
const outputImage = RawImage.fromTensor(imageData);
outputImage.save('output.png');

Inputs

Image	Trimap

Outputs

Quantized	Unquantized

---

TODOs:

• Add pipeline + docs for image-matting task
• Add pipeline unit tests
• Get optimum PR merged: Add ONNX export for ViTMatte models optimum#1582

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[xenova]

Merging PR now, and will add image-matting pipeline once available in transformers.