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

arXiv: https://arxiv.org/abs/1909.12573 · HTML: https://mlsanity.com/paper/1909.12573/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 13 of 13)

- [Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations](https://mlsanity.com/paper/2204.08839/) (2022)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [Generative Models: What Do They Know? Do They Know Things? Let's Find Out!](https://mlsanity.com/paper/2311.17137/) (2023)
- [StyleGAN knows Normal, Depth, Albedo, and More](https://mlsanity.com/paper/2306.00987/) (2023)
- [3D-Aware Indoor Scene Synthesis with Depth Priors](https://mlsanity.com/paper/2202.08553/) (2022)
- [A Survey on Deep Generative 3D-aware Image Synthesis](https://mlsanity.com/paper/2210.14267/) (2022)
- [MVTrans: Multi-View Perception of Transparent Objects](https://mlsanity.com/paper/2302.11683/) (2023)
- [AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields](https://mlsanity.com/paper/2206.06100/) (2022)
- [Controllable Visual-Tactile Synthesis](https://mlsanity.com/paper/2305.03051/) (2023)
- [Unsupervised Learning of Depth and Depth-of-Field Effect from Natural Images with Aperture Rendering Generative Adversarial Networks](https://mlsanity.com/paper/2106.13041/) (2021)
- [Consistent Multimodal Generation via A Unified GAN Framework](https://mlsanity.com/paper/2307.01425/) (2023)
- [Deep Generative Models on 3D Representations: A Survey](https://mlsanity.com/paper/2210.15663/) (2022)
- [P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments](https://mlsanity.com/paper/2309.15526/) (2023)

## Abstract (arXiv)

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.