DiLO: Disentangled Latent Optimization for Learning Shape and Deformation in Grouped Deforming 3D Objects
This addresses the need for efficient and interpretable 3D object modeling in computer vision, though it appears incremental as it builds on latent optimization and encoder networks.
The paper tackles the problem of parameterizing grouped deforming 3D objects into shape and deformation factors without supervision, achieving results comparable or superior to more complex existing methods in tasks like deformation transfer and classification.
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.