Hair color simulation using a hair color classification guided network
Aspects of hair simulation, and networks therefor are provided including aspects to train such networks. There is provided a generative model for hair simulation that is guided during training by a hair classifier model. The generative model in an embodiment is provided for use in a virtual try-on (VTO) pipeline such as for virtually trying on hair color products. Further provided is a color mapping network to process an input image and target hair color for the generative model to define the hair simulation (e.g. as an output image with simulated hair color).
1 . A computing device comprising a processor coupled to storage device storing instructions executable by the processor to cause the computing device to:
process an input image and a target hair color using a virtual try on (VTO) pipeline to produce a VTO experience that simulates the target hair color with the input image to produce an output image;
wherein the VTO pipeline comprises a color refinement neural network to generate the output image combining the target hair color and the input image, the color refinement neural network comprising a generative neural network trained under guidance of a hair classification network comprising a shade classifier that outputs a hair shade value and a reflectance classifier that outputs a hair reflectance value for determining training loss information from output images for training the generative neural network.
2 . The computing device of claim 1 , wherein the instructions are executable by the processor to cause the computing device to provide an interface to one or both of: i) a color recommendation engine to recommend a target hair color; and ii) an e-commerce service with which to buy one or both of a product or service.
3 . The computing device of claim 1 , wherein the VTO pipeline comprises a color mapping network trained to produce a color map for input to the generative neural network to produce the output image for the VTO experience, the color map produced from features of the image, image hair color data determined from the image, and the target hair color.
4 . The computing device of claim 3 , wherein the color mapping network comprises an encoder to determine the features from the input image; a concatonator to combine the features, the target hair color and the image hair color data for processing by a first fully connected block, and a second block for processing an interim map from the first block with the image hair color data to produce the color map for input to the generative neural network.
5 . The computing device of claim 4 , wherein the VTO pipeline comprises a hair analysis engine for determining the image hair color data from the input image.
6 . The computing device of claim 1 , wherein the input image and target hair color are defined using RGB values such that the generative neural network is trained to produce an output image using particular RGB values as guided during the training by the hair classification network using hair shade values and reflectance values.
7 . The computing device of claim 6 , wherein the hair classification network is defined and trained according to an industry standard for hair color classification comprising a respective plurality of classes for hair shade and hair reflectance.
8 . The computing device of claim 1 , wherein the hair classification network comprises an encoding backbone and each of the shade classifier and the hair reflectance classifier comprises a respective linear classifier.
9 . The computing device of claim 8 , wherein the hair classification network having been defined through training with a sum of shade and reflectance cross entropy losses determined from i) outputs of hair shade values and hair reflectance values, and ii) target labels for hair shade and hair reflectance, the target labels prepared for hair classification network training images from respective expert votes by a plurality of experts.
10 . The computing device of claim 9 , wherein the target labels comprise soft labels for at least some of the training images, the soft label determined from an empirical distribution of the expert votes over the respective classes.
11 . The computing device of claim 9 , wherein one of
a. the hair classification network having been trained with respective annotator confusion matrices comprising a plurality (n) of shade annotator confusion matrices and a plurality (n) of reflectance annotator confusion matrices, wherein n is defined from a total number of experts providing the expert votes, and wherein the output from the shade classifier is multiplied by a respective one of the plurality of shade confusion matrices and wherein the output from the reflectance classifier is multiplied by a respective one of the plurality of reflectance confusion matrices to predict the vote of a respective one of the plurality of experts; and wherein the neural network and respective annotator confusion matrices are trained together; or
b. the hair classification network having been trained in accordance with a mean teacher framework.
12 . A method of configuring a neural network that classifies hair shade and hair reflectance of hair in an input image, the method comprising:
providing the neural network, the neural network comprising an encoding backbone coupled to i) a shade classifier that outputs a hair shade value and ii) a reflectance classifier that outputs a hair reflectance value, each classifier comprising a linear classifier;
providing a plurality of training images associated with respective training labels for each of hair shade and hair reflectance, the target labels prepared from respective expert votes by a plurality of experts; and
training the neural network using the training images, the training performed in accordance with a sum of shade and reflectance cross entropy losses determined from i) classifier outputs of the hair shade values and hair reflectance values, and ii) the target labels.
13 . The method of claim 12 , wherein the training comprises training the neural network using a mean teacher framework.
14 . The method of claim 12 , wherein the training comprises training the neural network using respective annotator confusion matrices comprising a plurality (n) of shade annotator confusion matrices and a plurality (n) of reflectance annotator confusion matrices, wherein n is defined from a total number of experts providing the expert votes, and wherein the output from the shade classifier is multiplied by a respective one of the plurality of shade confusion matrices and wherein the output from the reflectance classifier is multiplied by a respective one of the plurality of reflectance confusion matrices to predict the vote of a respective one of the plurality of experts; and wherein the neural network and respective annotator confusion matrices are trained together.
15 . A method comprising:
providing a generative neural network that generates an output image combining a target hair color with an input image;
providing a hair classification network as a component of a discriminator of the generative neural network, the hair classification network comprising i) a shade classifier that determines an output hair shade and ii) a reflectance classifier that determines an output hair reflectance;
determining training loss information using the target hair color and the output hair shade, and output hair reflectance; and
training the generative neural network under guidance of the hair classification network using the training loss information.
16 . The method of claim 15 , wherein the target hair color, input image and output image are defined using RGB type data and the output hair shade and output hair reflectance are defined in accordance with an industry standard for hair color classification comprising a respective plurality of classes for hair shade and hair reflectance.
17 . The method of claim 15 comprising, prior to training the generative neural network, pre-training a color mapping network configured to process the input image and, image hair color data from hair pixels of the input image and the target hair color to provide a color map to the generative neural network for generating the output image from the input image.