paper-with-me

홈 › Papers

RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models

2025-07-24 · Shen Zhu, Yinzhu Jin, Tyler Spears, Ifrah Zawar, P. Thomas Fletcher 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.

📄 PDF Abstract BibTeX arXiv:2507.18830

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Leveraging Diffusion Knowledge for Generative Image Compression with Fractal Frequency-Aware Band Learning

2025-03-14 · Lingyu Zhu, Xiangrui Zeng, Bolin Chen, Peilin Chen 외

By optimizing the rate-distortion-realism trade-off, generative image compression approaches produce detailed, realistic images instead of the only sharp-looking reconstructions produced by rate-distortion-optimized mode…

Image CompressionImage ReconstructionNavigate

DMD-augmented Unpaired Neural Schrödinger Bridge for Ultra-Low Field MRI Enhancement

2026-03-04 · Youngmin Kim, Jaeyun Shin, Jeongchan Kim, Taehoon Lee 외 arxiv

Ultra Low Field (64 mT) brain MRI improves accessibility but suffers from reduced image quality compared to 3 T. As paired 64 mT - 3 T scans are scarce, we propose an unpaired 64 mT $\rightarrow$ 3 T translation framewor…

Enhancing Privacy: The Utility of Stand-Alone Synthetic CT and MRI for Tumor and Bone Segmentation

2025-06-13 · André Ferreira, Kunpeng Xie, Caroline Wilpert, Gustavo Correia 외

AI requires extensive datasets, while medical data is subject to high data protection. Anonymization is essential, but poses a challenge for some regions, such as the head, as identifying structures overlap with regions …

MS-SSIMSegmentationSSIMTumor Segmentation

A Joint Graph and Image Convolution Network for Automatic Brain Tumor Segmentation

2021-09-12 · Camillo Saueressig, Adam Berkley, Reshma Munbodh, Ritambhara Singh

We present a joint graph convolution-image convolution neural network as our submission to the Brain Tumor Segmentation (BraTS) 2021 challenge. We model each brain as a graph composed of distinct image regions, which is …

Brain Tumor SegmentationGraph Neural NetworkSegmentationTumor Segmentation

Enhancing Photorealism Enhancement

2021-05-10 · Stephan R. Richter, Hassan Abu Alhaija, Vladlen Koltun

We present an approach to enhancing the realism of synthetic images. The images are enhanced by a convolutional network that leverages intermediate representations produced by conventional rendering pipelines. The networ…

Image-to-Image TranslationTranslation