Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild

TL;DR

This paper introduces a robust neural implicit modeling framework for high-quality 3D vehicle reconstruction from sparse, real-world data, leveraging shape priors, regularization, and curriculum learning to outperform existing methods.

Contribution

It proposes a novel combination of a deep encoder, regularized test-time optimization, a shape prior discriminator, and curriculum learning for improved in-the-wild 3D shape reconstruction.

Findings

Outperforms state-of-the-art methods on real-world datasets

Better captures global shape structure in sparse and occluded data

Achieves high-quality 3D reconstructions from single-view observations

Abstract

Reconstructing high-quality 3D objects from sparse, partial observations from a single view is of crucial importance for various applications in computer vision, robotics, and graphics. While recent neural implicit modeling methods show promising results on synthetic or dense data, they perform poorly on sparse and noisy real-world data. We discover that the limitations of a popular neural implicit model are due to lack of robust shape priors and lack of proper regularization. In this work, we demonstrate highquality in-the-wild shape reconstruction using: (i) a deep encoder as a robust-initializer of the shape latent-code; (ii) regularized test-time optimization of the latent-code; (iii) a deep discriminator as a learned high-dimensional shape prior; (iv) a novel curriculum learning strategy that allows the model to learn shape priors on synthetic data and smoothly transfer them to sparse real world data. Our approach better captures the global structure, performs well on occluded and sparse observations, and registers well with the ground-truth shape. We demonstrate superior performance over state-of-the-art 3D object reconstruction methods on two real-world datasets.