# Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis

arXiv: https://arxiv.org/abs/2402.16506 · HTML: https://mlsanity.com/paper/2402.16506/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 48 of its 55 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 48)

- [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)
- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions](https://mlsanity.com/paper/2102.05379/) (2021)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [SEAN: Image Synthesis with Semantic Region-Adaptive Normalization](https://mlsanity.com/paper/1911.12861/) (2019)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)
- [Pretraining is All You Need for Image-to-Image Translation](https://mlsanity.com/paper/2205.12952/) (2022)

## Built on by (most cited first, 11 of 11)

- [Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems](https://mlsanity.com/paper/2407.16125/) (2024)
- [Constant Acceleration Flow](https://mlsanity.com/paper/2411.00322/) (2024)
- [Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Models](https://mlsanity.com/paper/2506.10634/) (2025)
- [Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers](https://mlsanity.com/paper/2510.21986/) (2025)
- [Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models](https://mlsanity.com/paper/2509.22723/) (2025)
- [Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation](https://mlsanity.com/paper/2510.21167/) (2025)
- [DA-Font: Few-Shot Font Generation via Dual-Attention Hybrid Integration](https://mlsanity.com/paper/2509.16632/) (2025)
- [Example-Based Feature Painting on Textures](https://mlsanity.com/paper/2511.01513/) (2025)
- [Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance](https://mlsanity.com/paper/2603.03692/) (2026)
- [One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set Prediction](https://mlsanity.com/paper/2604.18344/) (2026)
- [Abdominal Ultrasound Simulation from Semantic Labels using Paired Label-to-Physics-Based Image Translation](https://mlsanity.com/paper/2610.08849/) (2026)

## Abstract (arXiv)

Semantic image synthesis (SIS) is a task to generate realistic images corresponding to semantic maps (labels). However, in real-world applications, SIS often encounters noisy user inputs. To address this, we propose Stochastic Conditional Diffusion Model (SCDM), which is a robust conditional diffusion model that features novel forward and generation processes tailored for SIS with noisy labels. It enhances robustness by stochastically perturbing the semantic label maps through Label Diffusion, which diffuses the labels with discrete diffusion. Through the diffusion of labels, the noisy and clean semantic maps become similar as the timestep increases, eventually becoming identical at t=T. This facilitates the generation of an image close to a clean image, enabling robust generation. Furthermore, we propose a class-wise noise schedule to differentially diffuse the labels depending on the class. We demonstrate that the proposed method generates high-quality samples through extensive experiments and analyses on benchmark datasets, including a novel experimental setup simulating human errors during real-world applications. Code is available at https://github.com/mlvlab/SCDM.