# PosDiffAE: Position-aware Diffusion Auto-encoder For High-Resolution Brain Tissue Classification Incorporating Artifact Restoration

arXiv: https://arxiv.org/abs/2507.02405 · HTML: https://mlsanity.com/paper/2507.02405/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 3 Jul 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Diffusion Self-Guidance for Controllable Image Generation](https://mlsanity.com/paper/2306.00986/) (2023)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [Denoising Diffusion Autoencoders are Unified Self-supervised Learners](https://mlsanity.com/paper/2303.09769/) (2023)
- [Diffusion Model as Representation Learner](https://mlsanity.com/paper/2308.10916/) (2023)
- [Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations](https://mlsanity.com/paper/2008.05571/) (2020)
- [Towards Flexible Blind JPEG Artifacts Removal](https://mlsanity.com/paper/2109.14573/) (2021)
- [A Morphology Focused Diffusion Probabilistic Model for Synthesis of Histopathology Images](https://mlsanity.com/paper/2209.13167/) (2022)
- [Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models](https://mlsanity.com/paper/2212.12990/) (2022)
- [UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation](https://mlsanity.com/paper/2203.02557/) (2022)
- [Self-supervised driven consistency training for annotation efficient histopathology image analysis](https://mlsanity.com/paper/2102.03897/) (2021)
- [Swin MAE: Masked Autoencoders for Small Datasets](https://mlsanity.com/paper/2212.13805/) (2022)
- [DriftRec: Adapting diffusion models to blind JPEG restoration](https://mlsanity.com/paper/2211.06757/) (2022)
- [ViT-DAE: Transformer-driven Diffusion Autoencoder for Histopathology Image Analysis](https://mlsanity.com/paper/2304.01053/) (2023)
- [Diffusion-based generation of Histopathological Whole Slide Images at a Gigapixel scale](https://mlsanity.com/paper/2311.08199/) (2023)
- [Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections](https://mlsanity.com/paper/2011.12865/) (2020)
- [Artifact Restoration in Histology Images with Diffusion Probabilistic Models](https://mlsanity.com/paper/2307.14262/) (2023)
- [Histopathology Image Classification using Deep Manifold Contrastive Learning](https://mlsanity.com/paper/2306.14459/) (2023)
- [Denoising Diffusion Probabilistic Models for Image Inpainting of Cell Distributions in the Human Brain](https://mlsanity.com/paper/2311.16821/) (2023)

## Built on by (most cited first, 3 of 3)

- [AD-DAE: Alzheimer's Disease Progression Modeling with Unpaired Longitudinal MRI using Diffusion Auto-Encoders](https://mlsanity.com/paper/2511.05934/) (2025)
- [CytoCLIP: Learning Cytoarchitectural Characteristics in Developing Human Brain Using Contrastive Language Image Pre-Training](https://mlsanity.com/paper/2601.12282/) (2026)
- [Diffusion Autoencoder for Unsupervised Artifact Restoration in Handheld Fundus Images](https://mlsanity.com/paper/2604.15723/) (2026)

## Abstract (arXiv)

Denoising diffusion models produce high-fidelity image samples by capturing the image distribution in a progressive manner while initializing with a simple distribution and compounding the distribution complexity. Although these models have unlocked new applicabilities, the sampling mechanism of diffusion does not offer means to extract image-specific semantic representation, which is inherently provided by auto-encoders. The encoding component of auto-encoders enables mapping between a specific image and its latent space, thereby offering explicit means of enforcing structures in the latent space. By integrating an encoder with the diffusion model, we establish an auto-encoding formulation, which learns image-specific representations and offers means to organize the latent space. In this work, First, we devise a mechanism to structure the latent space of a diffusion auto-encoding model, towards recognizing region-specific cellular patterns in brain images. We enforce the representations to regress positional information of the patches from high-resolution images. This creates a conducive latent space for differentiating tissue types of the brain. Second, we devise an unsupervised tear artifact restoration technique based on neighborhood awareness, utilizing latent representations and the constrained generation capability of diffusion models during inference. Third, through representational guidance and leveraging the inference time steerable noising and denoising capability of diffusion, we devise an unsupervised JPEG artifact restoration technique.