DiLO: Disentangled Latent Optimization for Learning Shape and Deformation in Grouped Deforming 3D Objects

TL;DR

This paper introduces DiLO, a novel unsupervised method for disentangling shape and deformation factors in 3D objects, enabling effective applications like transfer and classification.

Contribution

It presents a disentangled latent optimization approach with efficient inference, outperforming complex existing methods in various 3D object datasets.

Findings

Effective in deformation transfer and classification

Comparable or superior to existing complex methods

Works across human, animal, and facial datasets

Abstract

In this work, we propose a disentangled latent optimization-based method for parameterizing grouped deforming 3D objects into shape and deformation factors in an unsupervised manner. Our approach involves the joint optimization of a generator network along with the shape and deformation factors, supported by specific regularization techniques. For efficient amortized inference of disentangled shape and deformation codes, we train two order-invariant PoinNet-based encoder networks in the second stage of our method. We demonstrate several significant downstream applications of our method, including unsupervised deformation transfer, deformation classification, and explainability analysis. Extensive experiments conducted on 3D human, animal, and facial expression datasets demonstrate that our simple approach is highly effective in these downstream tasks, comparable or superior to existing methods with much higher complexity.