3D reconstruction is the process of capturing the shape and appearance of real objects. Parametric 3D models have enabled a wide variety of tasks in computer graphics and vision, such as modeling human bodies, faces, and hands. However, the construction of these parametric models is often tedious, as it requires heavy manual tweaking, and they struggle to represent additional complexity and details such as wrinkles or clothing.

We propose to use an algebraic implicit surface method to model the 3D surface of the human body. It is evident that 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 superiority 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 proposed approach is expected to learn some alternative methods, irrespective of the traditional parametric 3D models. Hence, it is expected that the proposed approach shall be in requisite of some handcrafted constraints to cope up with object specifications, primarily concentrating on disentangled 4D dynamics into latent space for the representation of human body shape and posture. This will be an enabler to leverage the flexibility developed recently into the learned implicit functions, and further fit the newly learned observations optimally into the parametric models for recognition of human shape and posture. Bearing to this, a significant impact is expected in terms of better accuracy and more detailing in the representation of the observed deformed sequences.