RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis

Abstract

Understanding three-dimensional (3D) geometries from two-dimensional (2D) images without any labeled information is promising for understanding the real world without incurring annotation cost. We herein propose a novel generative model, RGBD-GAN, which achieves unsupervised 3D representation learning from 2D images. The proposed method enables camera parameter-conditional image generation and depth image generation without any 3D annotations, such as camera poses or depth. We use an explicit 3D consistency loss for two RGBD images generated from different camera parameters, in addition to the ordinal GAN objective. The loss is simple yet effective for any type of image generator such as DCGAN and StyleGAN to be conditioned on camera parameters. Through experiments, we demonstrated that the proposed method could learn 3D representations from 2D images with various generator architectures.

arXiv comment21 pages, ICLR2020

References in corpus (9)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Which Training Methods for GANs do actually Converge?
• Unsupervised Learning of Depth and Ego-Motion from Video
• Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
• Unsupervised Learning of 3D Structure from Images

Cited by in corpus (6)

• Mimicry: Towards the Reproducibility of GAN Research
• Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
• Learning Neural Light Transport
• 3DMaterialGAN: Learning 3D Shape Representation from Latent Space for Materials Science Applications
• P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments
• Manipulation of Camera Sensor Data via Fault Injection for Anomaly Detection Studies in Verification and Validation Activities For AI