Computer Vision135 [2025-1] 최민서 - Denoising Diffusion Implicit Models [DDIM] https://arxiv.org/abs/2010.02502 Denoising Diffusion Implicit ModelsDenoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusionarxiv.org 본 논문은 Denoising Diffusion Probabilistic Models(DDPM)와 깊은 .. 2025. 2. 21. [2025-1] 주서영 - Flow matching for generative modeling Flow MatchingICLR 2023850회 인용1. Introduction본 논문은 Continuous Normalizaing Flows(CNF)를 시뮬레이션 없이(simulation-free) 효율적으로 훈련할 수 있는 학습 방법인 Flow Matching (FM)을 제시한다.2. Preliminaries : Continuous Normalizing FlowsNormalizaing Flow : 데이터 분포인 $x$에서 $z$로의 역변환이 가능한 Flow를 학습하는 모델Continuous Normalizing Flows(CNF) : 시간에 따른 vector filed를 학습하여 ODE를 통해 확률 분포를 변환하는 생성 모델$\mathbb{R}^d$데이터 포인트 $x=(x^1,\cdots,x^d)\i.. 2025. 2. 20. [25-1] 박지원 - Deep-Emotion: Facial Expression RecognitionUsing Attentional Convolutional Network Original paper ) https://arxiv.org/abs/1902.01019 Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional NetworkFacial expression recognition has been an active research area over the past few decades, and it is still challenging due to the high intra-class variation. Traditional approaches for this problem rely on hand-crafted features such as SIFT, HOG and LBP, foarxiv.or.. 2025. 2. 19. [2025-1] 주서영 - Adding Conditional Control to Text-to-Image Diffusion Models ControlNetGitHub GitHub - lllyasviel/ControlNet: Let us control diffusion models!Let us control diffusion models! Contribute to lllyasviel/ControlNet development by creating an account on GitHub.github.comICCV 20233626회 인용1. Introduction기존 Text-Image 모델(Stable Diffusion, DALL·E 2, MidJourney, etc.)은 이미지 생성은 뛰어났지만 프롬프트를 수정하며 원하는 결과를 얻기까지 반복 작업이 필요하고 Fine-tuning에서는 데이터셋과 훈련 비용 등에 문제가 있었음ControlNet.. 2025. 2. 15. 이전 1 ··· 9 10 11 12 13 14 15 ··· 34 다음
