# Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generation

arXiv: https://arxiv.org/abs/1705.07202 · HTML: https://mlsanity.com/paper/1705.07202/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2017.

## Built on by (most cited first, 18 of 18)

- [Spectral Image Tokenizer](https://mlsanity.com/paper/2412.09607/) (2024)
- [High-Resolution Image Editing via Multi-Stage Blended Diffusion](https://mlsanity.com/paper/2210.12965/) (2022)
- [DoseDiff: Distance-aware Diffusion Model for Dose Prediction in Radiotherapy](https://mlsanity.com/paper/2306.16324/) (2023)
- [Airfoil GAN: Encoding and Synthesizing Airfoils for Aerodynamic Shape Optimization](https://mlsanity.com/paper/2101.04757/) (2021)
- [Coupled Variational Autoencoder](https://mlsanity.com/paper/2306.02565/) (2023)
- [Robust Vector Quantized-Variational Autoencoder](https://mlsanity.com/paper/2202.01987/) (2022)
- [A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps](https://mlsanity.com/paper/2212.06717/) (2022)
- [NPB-REC: A Non-parametric Bayesian Deep-learning Approach for Undersampled MRI Reconstruction with Uncertainty Estimation](https://mlsanity.com/paper/2404.04550/) (2024)
- [Towards a framework on tabular synthetic data generation: a minimalist approach: theory, use cases, and limitations](https://mlsanity.com/paper/2411.10982/) (2024)
- [Unsupervised dynamic modeling of medical image transformation](https://mlsanity.com/paper/2103.00930/) (2021)
- [Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder](https://mlsanity.com/paper/2207.09783/) (2022)
- [Assessing Image Quality Using a Simple Generative Representation](https://mlsanity.com/paper/2404.18178/) (2024)
- [A Deep Learning Generative Model Approach for Image Synthesis of Plant Leaves](https://mlsanity.com/paper/2111.03388/) (2021)
- [Futuristic Variations and Analysis in Fundus Images Corresponding to Biological Traits](https://mlsanity.com/paper/2302.03839/) (2023)
- [Scene Graph Conditioning in Latent Diffusion](https://mlsanity.com/paper/2310.10338/) (2023)
- [Advancing Generative Model Evaluation: A Novel Algorithm for Realistic Image Synthesis and Comparison in OCR System](https://mlsanity.com/paper/2402.17204/) (2024)
- [Beyond Traditional Single Object Tracking: A Survey](https://mlsanity.com/paper/2405.10439/) (2024)
- [In the Blink of an Eye: Instant Game Map Editing using a Generative-AI Smart Brush](https://mlsanity.com/paper/2503.19793/) (2025)

## Abstract (arXiv)

Variational auto-encoder (VAE) is a powerful unsupervised learning framework for image generation. One drawback of VAE is that it generates blurry images due to its Gaussianity assumption and thus L2 loss. To allow the generation of high quality images by VAE, we increase the capacity of decoder network by employing residual blocks and skip connections, which also enable efficient optimization. To overcome the limitation of L2 loss, we propose to generate images in a multi-stage manner from coarse to fine. In the simplest case, the proposed multi-stage VAE divides the decoder into two components in which the second component generates refined images based on the course images generated by the first component. Since the second component is independent of the VAE model, it can employ other loss functions beyond the L2 loss and different model architectures. The proposed framework can be easily generalized to contain more than two components. Experiment results on the MNIST and CelebA datasets demonstrate that the proposed multi-stage VAE can generate sharper images as compared to those from the original VAE.