# High-Fidelity Synthesis with Disentangled Representation

arXiv: https://arxiv.org/abs/2001.04296 · HTML: https://mlsanity.com/paper/2001.04296/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2020.

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

- [DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents](https://mlsanity.com/paper/2201.00308/) (2022)
- [GIRAFFE HD: A High-Resolution 3D-aware Generative Model](https://mlsanity.com/paper/2203.14954/) (2022)
- [CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields](https://mlsanity.com/paper/2103.17269/) (2021)
- [WarpedGANSpace: Finding non-linear RBF paths in GAN latent space](https://mlsanity.com/paper/2109.13357/) (2021)
- [STEEX: Steering Counterfactual Explanations with Semantics](https://mlsanity.com/paper/2111.09094/) (2021)
- [Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View](https://mlsanity.com/paper/2102.10543/) (2021)
- [EigenGAN: Layer-Wise Eigen-Learning for GANs](https://mlsanity.com/paper/2104.12476/) (2021)
- [Detecting and Recovering Sequential DeepFake Manipulation](https://mlsanity.com/paper/2207.02204/) (2022)
- [StyleFusion: A Generative Model for Disentangling Spatial Segments](https://mlsanity.com/paper/2107.07437/) (2021)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Towards Building A Group-based Unsupervised Representation Disentanglement Framework](https://mlsanity.com/paper/2102.10303/) (2021)
- [3D-Aware Video Generation](https://mlsanity.com/paper/2206.14797/) (2022)
- [Tensor Component Analysis for Interpreting the Latent Space of GANs](https://mlsanity.com/paper/2111.11736/) (2021)
- [Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis](https://mlsanity.com/paper/2207.10257/) (2022)
- [Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedback](https://mlsanity.com/paper/2402.02346/) (2024)
- [Robust Sequential DeepFake Detection](https://mlsanity.com/paper/2309.14991/) (2023)
- [Cluster-guided Image Synthesis with Unconditional Models](https://mlsanity.com/paper/2112.12911/) (2021)
- [SolarGAN: Synthetic Annual Solar Irradiance Time Series on Urban Building Facades via Deep Generative Networks](https://mlsanity.com/paper/2206.00747/) (2022)
- [Learning Disentangled Representations for Generalized Multi-view Clustering](https://mlsanity.com/paper/2605.15640/) (2026)
- [Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models](https://mlsanity.com/paper/2204.08573/) (2022)
- [DOT-VAE: Disentangling One Factor at a Time](https://mlsanity.com/paper/2210.10920/) (2022)
- [Disentangled Representation Learning Using (β-)VAE and GAN](https://mlsanity.com/paper/2208.04549/) (2022)
- [Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization](https://mlsanity.com/paper/2410.20573/) (2024)

## Abstract (arXiv)

Learning disentangled representation of data without supervision is an important step towards improving the interpretability of generative models. Despite recent advances in disentangled representation learning, existing approaches often suffer from the trade-off between representation learning and generation performance i.e. improving generation quality sacrifices disentanglement performance). We propose an Information-Distillation Generative Adversarial Network (ID-GAN), a simple yet generic framework that easily incorporates the existing state-of-the-art models for both disentanglement learning and high-fidelity synthesis. Our method learns disentangled representation using VAE-based models, and distills the learned representation with an additional nuisance variable to the separate GAN-based generator for high-fidelity synthesis. To ensure that both generative models are aligned to render the same generative factors, we further constrain the GAN generator to maximize the mutual information between the learned latent code and the output. Despite the simplicity, we show that the proposed method is highly effective, achieving comparable image generation quality to the state-of-the-art methods using the disentangled representation. We also show that the proposed decomposition leads to an efficient and stable model design, and we demonstrate photo-realistic high-resolution image synthesis results (1024x1024 pixels) for the first time using the disentangled representations.