Inferring 3D object structures from a single image is an ill-posed task due
to depth ambiguity and occlusion. Typical resolutions in the literature include
leveraging 2D or 3D ground truth for supervised learning, as well as imposing
hand-crafted symmetry priors or using an implicit representation to hallucinate
novel viewpoints for unsupervised methods. In this work, we propose a general
adversarial learning framework for solving Unsupervised 2D to Explicit 3D Style
Transfer (UE3DST). Specifically, we merge two architectures: the unsupervised
explicit 3D reconstruction network of Wu et al.\ and the Generative Adversarial
Network (GAN) named StarGAN-v2. We experiment across three facial datasets
(Basel Face Model, 3DFAW and CelebA-HQ) and show that our solution is able to
outperform well established solutions such as DepthNet in 3D reconstruction and
Pix2NeRF in conditional style transfer, while we also justify the individual
contributions of our model components via ablation. In contrast to the
aforementioned baselines, our scheme produces features for explicit 3D
rendering, which can be manipulated and utilized in downstream tasks.

本文旨在提出一种解决由于深度歧义和遮挡而导致的从单个图像推断三维物体结构的无监督方法 ——Unsupervised 2D 到 Explicit 3D Style Transfer (UE3DST)，我们提出了一个通用的对抗学习框架，通过将 Wu 等人的无监督明确 3D 重建网络和 StarGAN-v2 之类的生成对抗网络 (GAN) 进行合并，我们在三个面部数据集 (Basel Face Model、3DFAW 和 CelebA-HQ) 上进行实验，结果表明我们的解决方案能够胜过 DepthNet 在 3D 重建和 Pix2NeRF 在条件样式转移方面已经建立的解决方案，相比之下，我们的方案产生了用于明确 3D 渲染的特征，可以在下游任务中进行操作和利用。