Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition

TL;DR

This paper introduces an autoencoder that jointly performs neural rendering and intrinsic image decomposition using unpaired data, enabling realistic image synthesis and scene understanding without extensive labeled datasets.

Contribution

It proposes a novel autoencoder framework that learns photo-realistic rendering and intrinsic decomposition from unpaired data, removing the need for detailed scene annotations.

Findings

Outperforms state-of-the-art image translation methods

Learns realistic rendering from limited 3D models and unaligned images

Provides accurate intrinsic decompositions without paired ground truth

Abstract

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been proposed for this task, acquiring a dataset of images with accurately aligned 3D models is very difficult. The main contribution of this work is to lift this restriction by training a neural rendering algorithm from unpaired data. More specifically, we propose an autoencoder for joint generation of realistic images from synthetic 3D models while simultaneously decomposing real images into their intrinsic shape and appearance properties. In contrast to a traditional graphics pipeline, our approach does not require to specify all scene properties, such as material parameters and lighting by hand. Instead, we learn photo-realistic deferred rendering from a small set of 3D models and a larger set of unaligned real images, both of which are easy to acquire in practice. Simultaneously, we obtain accurate intrinsic decompositions of real images while not requiring paired ground truth. Our experiments confirm that a joint treatment of rendering and decomposition is indeed beneficial and that our approach outperforms state-of-the-art image-to-image translation baselines both qualitatively and quantitatively.