# IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis

arXiv: https://arxiv.org/abs/1807.06358 · HTML: https://mlsanity.com/paper/1807.06358/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2018.

## Built on by (most cited first, 30 of 85)

- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](https://mlsanity.com/paper/2403.06976/) (2024)
- [A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis](https://mlsanity.com/paper/2306.14544/) (2023)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review](https://mlsanity.com/paper/2307.13125/) (2023)
- [A Good Score Does not Lead to A Good Generative Model](https://mlsanity.com/paper/2401.04856/) (2024)
- [BrushEdit: All-In-One Image Inpainting and Editing](https://mlsanity.com/paper/2412.10316/) (2024)
- [Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2306.09869/) (2023)
- [LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model](https://mlsanity.com/paper/2403.11929/) (2024)
- [Isometric Representation Learning for Disentangled Latent Space of Diffusion Models](https://mlsanity.com/paper/2407.11451/) (2024)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors](https://mlsanity.com/paper/2411.07472/) (2024)
- [NWT: Towards natural audio-to-video generation with representation learning](https://mlsanity.com/paper/2106.04283/) (2021)
- [Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting](https://mlsanity.com/paper/2207.04624/) (2022)
- [Securing Deep Generative Models with Universal Adversarial Signature](https://mlsanity.com/paper/2305.16310/) (2023)
- [Improved Training Technique for Latent Consistency Models](https://mlsanity.com/paper/2502.01441/) (2025)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penalty](https://mlsanity.com/paper/2212.12641/) (2022)
- [Chaining text-to-image and large language model: A novel approach for generating personalized e-commerce banners](https://mlsanity.com/paper/2403.05578/) (2024)
- [Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statistics](https://mlsanity.com/paper/2405.18790/) (2024)
- [DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation](https://mlsanity.com/paper/2411.04168/) (2024)
- [Learning cortical representations through perturbed and adversarial dreaming](https://mlsanity.com/paper/2109.04261/) (2021)
- [KIND: Knowledge Integration and Diversion for Training Decomposable Models](https://mlsanity.com/paper/2408.07337/) (2024)
- [Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2505.16379/) (2025)
- [This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation](https://mlsanity.com/paper/2302.02150/) (2023)
- [Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey](https://mlsanity.com/paper/2411.05027/) (2024)
- [Master Face Attacks on Face Recognition Systems](https://mlsanity.com/paper/2109.03398/) (2021)
- [CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis](https://mlsanity.com/paper/2411.16783/) (2024)
- [Are generative models fair? A study of racial bias in dermatological image generation](https://mlsanity.com/paper/2501.11752/) (2025)
- [CVAD: A generic medical anomaly detector based on Cascade VAE](https://mlsanity.com/paper/2110.15811/) (2021)

## Abstract (arXiv)

We present a novel introspective variational autoencoder (IntroVAE) model for synthesizing high-resolution photographic images. IntroVAE is capable of self-evaluating the quality of its generated samples and improving itself accordingly. Its inference and generator models are jointly trained in an introspective way. On one hand, the generator is required to reconstruct the input images from the noisy outputs of the inference model as normal VAEs. On the other hand, the inference model is encouraged to classify between the generated and real samples while the generator tries to fool it as GANs. These two famous generative frameworks are integrated in a simple yet efficient single-stream architecture that can be trained in a single stage. IntroVAE preserves the advantages of VAEs, such as stable training and nice latent manifold. Unlike most other hybrid models of VAEs and GANs, IntroVAE requires no extra discriminators, because the inference model itself serves as a discriminator to distinguish between the generated and real samples. Experiments demonstrate that our method produces high-resolution photo-realistic images (e.g., CELEBA images at (10242)), which are comparable to or better than the state-of-the-art GANs.