# CR-GAN: Learning Complete Representations for Multi-view Generation

arXiv: https://arxiv.org/abs/1806.11191 · HTML: https://mlsanity.com/paper/1806.11191/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2018.

## Built on by (most cited first, 23 of 23)

- [MoFaNeRF: Morphable Facial Neural Radiance Field](https://mlsanity.com/paper/2112.02308/) (2021)
- [Improved Transformer for High-Resolution GANs](https://mlsanity.com/paper/2106.07631/) (2021)
- [FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/2202.12972/) (2022)
- [TransFusion: Multi-view Divergent Fusion for Medical Image Segmentation with Transformers](https://mlsanity.com/paper/2203.10726/) (2022)
- [Joint Face Image Restoration and Frontalization for Recognition](https://mlsanity.com/paper/2105.09907/) (2021)
- [Deep Co-Attention Network for Multi-View Subspace Learning](https://mlsanity.com/paper/2102.07751/) (2021)
- [ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases](https://mlsanity.com/paper/2207.10670/) (2022)
- [Unsupervised Novel View Synthesis from a Single Image](https://mlsanity.com/paper/2102.03285/) (2021)
- [Scalable Infomin Learning](https://mlsanity.com/paper/2302.10701/) (2023)
- [A Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities](https://mlsanity.com/paper/2408.05436/) (2024)
- [AE-StyleGAN: Improved Training of Style-Based Auto-Encoders](https://mlsanity.com/paper/2110.08718/) (2021)
- [Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images](https://mlsanity.com/paper/2111.04237/) (2021)
- [Pose Attention-Guided Profile-to-Frontal Face Recognition](https://mlsanity.com/paper/2209.07001/) (2022)
- [Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesis](https://mlsanity.com/paper/2309.02340/) (2023)
- [FakeParts: a New Family of AI-Generated DeepFakes](https://mlsanity.com/paper/2508.21052/) (2025)
- [ID-Unet: Iterative Soft and Hard Deformation for View Synthesis](https://mlsanity.com/paper/2103.02264/) (2021)
- [Tensor Generalized Canonical Correlation Analysis](https://mlsanity.com/paper/2302.05277/) (2023)
- [Bengali Sign Language Recognition through Hand Pose Estimation using Multi-Branch Spatial-Temporal Attention Model](https://mlsanity.com/paper/2408.14111/) (2024)
- [Bidirectional Mammogram View Translation with Column-Aware and Implicit 3D Conditional Diffusion](https://mlsanity.com/paper/2510.04947/) (2025)
- [Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease](https://mlsanity.com/paper/2106.01416/) (2021)
- [Pixel Sampling for Style Preserving Face Pose Editing](https://mlsanity.com/paper/2106.07310/) (2021)
- [Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space](https://mlsanity.com/paper/2108.10265/) (2021)
- [Domain-Shared Learning and Gradual Alignment for Unsupervised Domain Adaptation Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2511.16184/) (2025)

## Abstract (arXiv)

Generating multi-view images from a single-view input is an essential yet challenging problem. It has broad applications in vision, graphics, and robotics. Our study indicates that the widely-used generative adversarial network (GAN) may learn "incomplete" representations due to the single-pathway framework: an encoder-decoder network followed by a discriminator network. We propose CR-GAN to address this problem. In addition to the single reconstruction path, we introduce a generation sideway to maintain the completeness of the learned embedding space. The two learning pathways collaborate and compete in a parameter-sharing manner, yielding considerably improved generalization ability to "unseen" dataset. More importantly, the two-pathway framework makes it possible to combine both labeled and unlabeled data for self-supervised learning, which further enriches the embedding space for realistic generations. The experimental results prove that CR-GAN significantly outperforms state-of-the-art methods, especially when generating from "unseen" inputs in wild conditions.