# FairDiff: Fair Segmentation with Point-Image Diffusion

arXiv: https://arxiv.org/abs/2407.06250 · HTML: https://mlsanity.com/paper/2407.06250/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 8 Jul 2024.

## Builds on (most cited first, 24 of 24)

- [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)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [You Only Need Adversarial Supervision for Semantic Image Synthesis](https://mlsanity.com/paper/2012.04781/) (2020)
- [Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions](https://mlsanity.com/paper/2401.03495/) (2024)
- [FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models](https://mlsanity.com/paper/2310.15160/) (2023)
- [WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis](https://mlsanity.com/paper/2402.19043/) (2024)
- [Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation](https://mlsanity.com/paper/2211.03364/) (2022)
- [From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds](https://mlsanity.com/paper/2301.13865/) (2023)
- [SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis](https://mlsanity.com/paper/2311.03355/) (2023)
- [DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection](https://mlsanity.com/paper/2304.13031/) (2023)
- [SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis](https://mlsanity.com/paper/2403.09638/) (2024)

## Built on by (most cited first, 15 of 15)

- [UniScene: Unified Occupancy-centric Driving Scene Generation](https://mlsanity.com/paper/2412.05435/) (2024)
- [Training-Free Model Merging for Multi-target Domain Adaptation](https://mlsanity.com/paper/2407.13771/) (2024)
- [PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model](https://mlsanity.com/paper/2503.19913/) (2025)
- [Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling](https://mlsanity.com/paper/2410.11236/) (2024)
- [Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method](https://mlsanity.com/paper/2510.22973/) (2025)
- [Diffusion-based Visual Anagram as Multi-task Learning](https://mlsanity.com/paper/2412.02693/) (2024)
- [Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification](https://mlsanity.com/paper/2409.17091/) (2024)
- [FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks](https://mlsanity.com/paper/2503.20784/) (2025)
- [Causal Disentanglement for Robust Long-tail Medical Image Generation](https://mlsanity.com/paper/2504.14450/) (2025)
- [PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation](https://mlsanity.com/paper/2603.22193/) (2026)
- [Artificial Intelligence for Biomedical Video Generation](https://mlsanity.com/paper/2411.07619/) (2024)
- [InvNeRF-Seg: Fine-Tuning a Pre-Trained NeRF for 3D Object Segmentation](https://mlsanity.com/paper/2504.05751/) (2025)
- [Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective](https://mlsanity.com/paper/2502.00619/) (2025)
- [DuetMoE: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Analysis](https://mlsanity.com/paper/2605.10521/) (2026)
- [FairGen: Preference-Aligned Diffusion for Demographically Equitable Medical Image Synthesis](https://mlsanity.com/paper/2606.14727/) (2026)

## Abstract (arXiv)

Fairness is an important topic for medical image analysis, driven by the challenge of unbalanced training data among diverse target groups and the societal demand for equitable medical quality. In response to this issue, our research adopts a data-driven strategy-enhancing data balance by integrating synthetic images. However, in terms of generating synthetic images, previous works either lack paired labels or fail to precisely control the boundaries of synthetic images to be aligned with those labels. To address this, we formulate the problem in a joint optimization manner, in which three networks are optimized towards the goal of empirical risk minimization and fairness maximization. On the implementation side, our solution features an innovative Point-Image Diffusion architecture, which leverages 3D point clouds for improved control over mask boundaries through a point-mask-image synthesis pipeline. This method outperforms significantly existing techniques in synthesizing scanning laser ophthalmoscopy (SLO) fundus images. By combining synthetic data with real data during the training phase using a proposed Equal Scale approach, our model achieves superior fairness segmentation performance compared to the state-of-the-art fairness learning models. Code is available at https://github.com/wenyi-li/FairDiff.