Diffusion3 [Paper Review] Classifier-Free Diffusion Guidance https://arxiv.org/abs/2207.12598 Classifier-Free Diffusion GuidanceClassifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier garxiv.org Introduce 이 논문은 classifier guidance 논문에서 classifier 을 사용하지 않고도 c.. 2025. 2. 5. [Paper Review] High-Resolution Image Synthesis with Latent Diffusion Models (Aka. Stable Diffusion) https://arxiv.org/abs/2112.10752 High-Resolution Image Synthesis with Latent Diffusion ModelsBy decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a guiding mechanism tarxiv.org 이번 주제는 아주 유명한 Stable Diffuion 논문을 리뷰해보도.. 2025. 2. 4. [Paper Review][Workflow Review] DreamFusion: Text-to-3D Using 2D Diffusion DreamFusion 은 Text input에 3D output을 결과로 하는 논문입니다.https://dreamfusion3d.github.io/ DreamFusion: Text-to-3D using 2D DiffusionDreamFusion: Text-to-3D using 2D Diffusion, 2022.dreamfusion3d.github.io 정말 간단하게 정리를 하자면,NeRF 를 사용하여 랜덤한 3D 물체를 렌더합니다.그리고 text 데이터를 input으로 넣으면 Stable Diffusion 을 이용하여 2D image 를 generate 합니다.generated 된 이미지와 NeRF 에서 렌더된 3D 이미지의 2D, 그리고 text prompt 를 SDS (Score Distillati.. 2025. 1. 23. 이전 1 다음
