Comparative Analysis of Generative Models: Enhancing Image Synthesis with VAEs, GANs, and Stable Diffusion

2024-08-16 · Sanchayan Vivekananthan

This paper examines three major generative modelling frameworks: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Stable Diffusion models. VAEs are effective at learning latent representations but frequently yield blurry results. GANs can generate realistic images but face issues such as mode collapse. Stable Diffusion models, while producing high-quality images with strong semantic coherence, are demanding in terms of computational resources. Additionally, the paper explores how incorporating Grounding DINO and Grounded SAM with Stable Diffusion improves image accuracy by utilising sophisticated segmentation and inpainting techniques. The analysis guides on selecting suitable models for various applications and highlights areas for further research.

📄 PDF Abstract BibTeX arXiv:2408.08751

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Residual Connection 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Multi-Head Attention 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Two-phase Hair Image Synthesis by Self-Enhancing Generative Model

2019-02-28 · Haonan Qiu, Chuan Wang, Hang Zhu, Xiangyu Zhu 외

Generating plausible hair image given limited guidance, such as sparse sketches or low-resolution image, has been made possible with the rise of Generative Adversarial Networks (GANs). Traditional image-to-image translat…

Image Generation Image-to-Image Translation Super-Resolution Translation+1

AI-based computer-aided diagnostic system of chest digital tomography synthesis: Demonstrating comparative advantage with X-ray-based AI systems

2022-06-18 · Kyung-Su Kim, Ju Hwan Lee, Seong Je Oh, Myung Jin Chung

Compared with chest X-ray (CXR) imaging, which is a single image projected from the front of the patient, chest digital tomosynthesis (CDTS) imaging can be more advantageous for lung lesion detection because it acquires …

Diagnostic Lesion Detection

MRI Cross-Modal Synthesis: A Comparative Study of Generative Models for T1-to-T2 Reconstruction

2026-02-05 · Ali Alqutayfi, Sadam Al-Azani arxiv

MRI cross-modal synthesis involves generating images from one acquisition protocol using another, offering considerable clinical value by reducing scan time while maintaining diagnostic information. This paper presents a…

MRI Reconstruction

Can Generative AI Replace Immunofluorescent Staining Processes? A Comparison Study of Synthetically Generated CellPainting Images from Brightfield

2024-06-15 · Xiaodan Xing, Siofra Murdoch, Chunling Tang, Giorgos Papanastasiou 외

Cell imaging assays utilizing fluorescence stains are essential for observing sub-cellular organelles and their responses to perturbations. Immunofluorescent staining process is routinely in labs, however the recent inno…

Image Generation

Vector quantization loss analysis in VQGANs: a single-GPU ablation study for image-to-image synthesis

2023-08-09 · Luv Verma, Varun Mohan

This study performs an ablation analysis of Vector Quantized Generative Adversarial Networks (VQGANs), concentrating on image-to-image synthesis utilizing a single NVIDIA A100 GPU. The current work explores the nuanced e…

GPU Image Generation Quantization