Iterative Superquadric Recomposition of 3D Objects from Multiple Views

TL;DR

The paper introduces ISCO, a model-free, iterative framework that reconstructs 3D objects from multiple views using superquadrics without training, achieving accurate, semantic, and out-of-distribution robust reconstructions.

Contribution

ISCO is a novel, training-free method that iteratively adds superquadrics for 3D object reconstruction from 2D images, emphasizing coarse-to-fine detail without semantic supervision.

Findings

ISCO outperforms recent superquadric methods in accuracy.

It is robust to out-of-distribution objects.

Provides consistent semantic parts across related objects.

Abstract

Humans are good at recomposing novel objects, i.e. they can identify commonalities between unknown objects from general structure to finer detail, an ability difficult to replicate by machines. We propose a framework, ISCO, to recompose an object using 3D superquadrics as semantic parts directly from 2D views without training a model that uses 3D supervision. To achieve this, we optimize the superquadric parameters that compose a specific instance of the object, comparing its rendered 3D view and 2D image silhouette. Our ISCO framework iteratively adds new superquadrics wherever the reconstruction error is high, abstracting first coarse regions and then finer details of the target object. With this simple coarse-to-fine inductive bias, ISCO provides consistent superquadrics for related object parts, despite not having any semantic supervision. Since ISCO does not train any neural network, it is also inherently robust to out-of-distribution objects. Experiments show that, compared to recent single instance superquadrics reconstruction approaches, ISCO provides consistently more accurate 3D reconstructions, even from images in the wild. Code available at https://github.com/ExplainableML/ISCO .