Generative Learning of Differentiable Object Models for Compositional Interpretation of Complex Scenes

TL;DR

This paper extends a scene interpretation autoencoder to handle multiple objects, improving decomposition and reconstruction quality through novel training modes and a new benchmark, advancing compositional scene understanding.

Contribution

The study introduces an extended DVP model capable of multi-object scene interpretation, with new training strategies and a more complex benchmark for evaluation.

Findings

Outperforms baselines in reconstruction quality

Better decomposition of overlapping objects

Enhanced training stability and efficiency

Abstract

This study builds on the architecture of the Disentangler of Visual Priors (DVP), a type of autoencoder that learns to interpret scenes by decomposing the perceived objects into independent visual aspects of shape, size, orientation, and color appearance. These aspects are expressed as latent parameters which control a differentiable renderer that performs image reconstruction, so that the model can be trained end-to-end with gradient using reconstruction loss. In this study, we extend the original DVP so that it can handle multiple objects in a scene. We also exploit the interpretability of its latent by using the decoder to sample additional training examples and devising alternative training modes that rely on loss functions defined not only in the image space, but also in the latent space. This significantly facilitates training, which is otherwise challenging due to the presence of extensive plateaus in the image-space reconstruction loss. To examine the performance of this approach, we propose a new benchmark featuring multiple 2D objects, which subsumes the previously proposed Multi-dSprites dataset while being more parameterizable. We compare the DVP extended in these ways with two baselines (MONet and LIVE) and demonstrate its superiority in terms of reconstruction quality and capacity to decompose overlapping objects. We also analyze the gradients induced by the considered loss functions, explain how they impact the efficacy of training, and discuss the limitations of differentiable rendering in autoencoders and the ways in which they can be addressed.