Deep Appearance Maps

TL;DR

This paper introduces Deep Appearance Maps (DAMs), a neural network-based representation of appearance that models color, orientation, viewer position, material, and illumination, enabling realistic synthesis and efficient appearance estimation.

Contribution

It presents a novel deep learning approach to directly represent and synthesize appearance as a 4D network, surpassing traditional reflectance and illumination models.

Findings

DAM can be learned from images or videos for appearance synthesis.

A network can map images to DAMs for quick appearance reproduction.

DAMs enable appearance estimation and segmentation across multiple materials.

Abstract

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.