3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces
This addresses the problem of low resolution and arbitrary shape handling in 3D reconstruction for computer vision applications, representing an incremental improvement over existing primitive-based methods.
The paper tackles 3D shape reconstruction from single RGB images by proposing a new primitive-based representation using constrained implicit algebraic surfaces, which achieves superior representation power compared to state-of-the-art methods and can semantically learn shape segments unsupervised.
3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of primitives for an arbitrary shape is challenging. To overcome these issues, we propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities and a deep neural network to produce these primitives. Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction. Furthermore, we show that our method can semantically learn segments of 3D shapes in an unsupervised manner. The code is publicly available from https://myavartanoo.github.io/3dias/ .