Deep Appearance Maps
This work addresses appearance representation for computer graphics and vision, offering a novel deep learning approach that is incremental over prior methods using classic parameters.
The authors tackled the problem of representing appearance (color, orientation, viewer position, material, illumination) by proposing Deep Appearance Maps (DAMs), a 4D neural network generalization of 2D reflectance maps, and demonstrated its use in synthesizing appearance from new conditions and mapping images to DAMs without lengthy optimization.
We propose a deep representation of appearance, i. e., the relation of color, surface orientation, viewer position, material and illumination. Previous approaches have useddeep learning to extract classic appearance representationsrelating to reflectance model parameters (e. g., Phong) orillumination (e. g., HDR environment maps). We suggest todirectly represent appearance itself as a network we call aDeep Appearance Map (DAM). This is a 4D generalizationover 2D reflectance maps, which held the view direction fixed. First, we show how a DAM can be learned from images or video frames and later be used to synthesize appearance, given new surface orientations and viewer positions. Second, we demonstrate how another network can be used to map from an image or video frames to a DAM network to reproduce this appearance, without using a lengthy optimization such as stochastic gradient descent (learning-to-learn). Finally, we show the example of an appearance estimation-and-segmentation task, mapping from an image showingmultiple materials to multiple deep appearance maps.