# Epsilon-VAE: Denoising as Visual Decoding

arXiv: https://arxiv.org/abs/2410.04081 · HTML: https://mlsanity.com/paper/2410.04081/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 86 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 30 of 64)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)

## Built on by (most cited first, 16 of 16)

- [Latent Denoising Makes Good Tokenizers](https://mlsanity.com/paper/2507.15856/) (2025)
- [VideoWorld 2: Learning Transferable Knowledge from Real-world Videos](https://mlsanity.com/paper/2602.10102/) (2026)
- [Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective](https://mlsanity.com/paper/2511.22249/) (2025)
- [WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction](https://mlsanity.com/paper/2508.05599/) (2025)
- [SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization](https://mlsanity.com/paper/2510.04961/) (2025)
- [Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion](https://mlsanity.com/paper/2603.14645/) (2026)
- [PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion](https://mlsanity.com/paper/2605.23902/) (2026)
- [VUGEN: Visual Understanding priors for GENeration](https://mlsanity.com/paper/2510.06529/) (2025)
- [Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement](https://mlsanity.com/paper/2510.07961/) (2025)
- [Adaptive 1D Video Diffusion Autoencoder](https://mlsanity.com/paper/2602.04220/) (2026)
- [Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization](https://mlsanity.com/paper/2510.23530/) (2025)
- [Local-Order Auxiliary Losses Can Improve Autoencoder Reconstruction](https://mlsanity.com/paper/2504.04202/) (2025)
- [RAC: Rectified Flow Auto Coder](https://mlsanity.com/paper/2603.05925/) (2026)
- [Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation](https://mlsanity.com/paper/2603.19570/) (2026)
- [Self-Reconstruction Dynamics for Autoencoder Reconstruction Refinement](https://mlsanity.com/paper/2609.32268/) (2026)
- [CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding](https://mlsanity.com/paper/2610.11376/) (2026)

## Abstract (arXiv)

In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for high-quality generation. Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input. In this work, we offer a new perspective by proposing denoising as decoding, shifting from single-step reconstruction to iterative refinement. Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image, guided by the latents provided by the encoder. We evaluate our approach by assessing both reconstruction (rFID) and generation quality (FID), comparing it to state-of-the-art autoencoding approaches. By adopting iterative reconstruction through diffusion, our autoencoder, namely Epsilon-VAE, achieves high reconstruction quality, which in turn enhances downstream generation quality by 22% at the same compression rates or provides 2.3x inference speedup through increasing compression rates. We hope this work offers new insights into integrating iterative generation and autoencoding for improved compression and generation.