Dense 3D Object Reconstruction from a Single Depth View

TL;DR

This paper introduces 3D-RecGAN++, a novel method that reconstructs complete 3D objects from a single depth view using GANs, outperforming existing approaches in accuracy and detail.

Contribution

The paper presents a new single-view 3D reconstruction method combining autoencoders and GANs, capable of high-resolution, detailed reconstructions from minimal input.

Findings

Outperforms state-of-the-art in single-view 3D reconstruction

Successfully reconstructs unseen object types

Achieves high-resolution 256^3 voxel reconstructions

Abstract

In this paper, we propose a novel approach, 3D-RecGAN++, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN++ only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid with a high resolution of 256^3 by recovering the occluded/missing regions. The key idea is to combine the generative capabilities of autoencoders and the conditional Generative Adversarial Networks (GAN) framework, to infer accurate and fine-grained 3D structures of objects in high-dimensional voxel space. Extensive experiments on large synthetic datasets and real-world Kinect datasets show that the proposed 3D-RecGAN++ significantly outperforms the state of the art in single view 3D object reconstruction, and is able to reconstruct unseen types of objects.