[논문 리뷰] CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion Kai He , Chin-Hsuan Wu , Igo...

[논문 리뷰] Flow Matching in Latent Space Flow Matching in Latent Space Quan Dao, Hao Phung CVPR 2023 [Arxiv] [Github] Flow Matching은 Diffusion에 비해 상대적으로 훈련하기 쉬우면서도 강력한 성능을 보여주는 생성 모델 알고...

[논문 리뷰] Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model Chunting Zhou, Lil...

[논문 리뷰] Analytic-Splatting : Anti-Aliased 3D Gaussian Splatting via Analytic Integration Analytic-Splatting : Anti-Aliased 3D Gaussian Splatting via Analytic Integration Zhihao Liang ECCV...

[논문 리뷰] Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering Zhiwen Yan, Weng Fei Low, Yu Chen, Gim Hee Lee CVPR 2024....

[논문 리뷰] 3D Gaussian Splatting for Real-Time Radiance Field Rendering 3D Gaussian Splatting for Real-Time Radiance Field Rendering Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George ...

[논문 리뷰] Learning Customized Visual Models with Retrieval-Augmented Knowledge 제목 : Learning Customized Visual Models with Retrieval-Augmented Knowledge 저자 : Haotian Liu, Kilho Son, Jianwei Ya...

[논문 리뷰] PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization 제목 : PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization 저자 : Junhy...

[논문 리뷰] DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation : arxiv 구글과 보스턴 연...

[논문 리뷰] TADA : Timestep-Awara Data Augmentation for Diffusion models 논문 링크 데이터 증강(Data Augmentation)은 주어진 원본 데이터를 확장하여 데이터셋의 다양성을 증가시키는 기법이다. 이 방법은 특히 학습 데이터가 부족한 경우, 모델의 일반화 능력을 향상시키기 위해 사용한다. ...