RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models
On the map: Diffusion models → Medical imaging and segmentation
Abstract (arXiv)
We propose image-to-image diffusion models that are designed to enhance the realism and details of generated brain images by introducing sharp edges, fine textures, subtle anatomical features, and imaging noise. Generative models have been widely adopted in the biomedical domain, especially in image generation applications. Latent diffusion models achieve state-of-the-art results in generating brain MRIs. However, due to latent compression, generated images from these models are overly smooth, lacking fine anatomical structures and scan acquisition noise that are typically seen in real images. This work formulates the realism enhancing and detail adding process as image-to-image diffusion models, which refines the quality of LDM-generated images. We employ commonly used metrics like FID and LPIPS for image realism assessment. Furthermore, we introduce new metrics to demonstrate the realism of images generated by RealDeal in terms of image noise distribution, sharpness, and texture.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 17 of its 26 references that are in the map. First posted on arXiv 24 Jul 2025.
Builds on
17 of 26 references.
Closest ancestors · 6
Same direction, newest first
- 2025MedIL: Implicit Latent Spaces for Generating Heterogeneous Medical Images at Arbitrary Resolutions12 Apr
- 2024Denoising Diffusion Models for 3D Healthy Brain Tissue Inpainting21 Mar
- 2024WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis29 Feb
- 2023Memory-Efficient 3D Denoising Diffusion Models for Medical Image Processing27 Mar
- 2023NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models20 Mar
- 2022Brain Imaging Generation with Latent Diffusion Models15 Sep
Other references · 11
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2021Image Super-Resolution via Iterative Refinementcited by 1,511
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
- 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
- 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
- 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 133
- 2023Patched Denoising Diffusion Models For High-Resolution Image Synthesiscited by 45
- 2023BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeyscited by 29
- 2024Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifoldcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024Physics-Informed Latent Diffusion for Multimodal Brain MRI Synthesis
- 2022Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation
- 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Review
- 2025Diffusion Models for conditional MRI generation
- 2023Natural scene reconstruction from fMRI signals using generative latent diffusion
- 2024Non-Reference Quality Assessment for Medical Imaging: Application to Synthetic Brain MRIs
- 2026Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
- 2022Spot the fake lungs: Generating Synthetic Medical Images using Neural Diffusion Models