Single-view Object Shape Reconstruction Using Deep Shape Prior and Silhouette

TL;DR

This paper introduces an online optimization approach for single-view 3D object shape reconstruction that leverages a deep shape prior and silhouette cues, avoiding end-to-end training.

Contribution

It presents a novel optimization-based framework using a deep autoencoder and probabilistic shape prior, differing from traditional end-to-end deep learning methods.

Findings

Achieves comparable results to state-of-the-art methods

Does not require training an end-to-end network

Demonstrates effectiveness of optimization-based shape inference

Abstract

3D shape reconstruction from a single image is a highly ill-posed problem. Modern deep learning based systems try to solve this problem by learning an end-to-end mapping from image to shape via a deep network. In this paper, we aim to solve this problem via an online optimization framework inspired by traditional methods. Our framework employs a deep autoencoder to learn a set of latent codes of 3D object shapes, which are fitted by a probabilistic shape prior using Gaussian Mixture Model (GMM). At inference, the shape and pose are jointly optimized guided by both image cues and deep shape prior without relying on an initialization from any trained deep nets. Surprisingly, our method achieves comparable performance to state-of-the-art methods even without training an end-to-end network, which shows a promising step in this direction.