본문 바로가기
  • 책상 밖 세상을 경험할 수 있는 Playground를 제공하고, 수동적 학습에서 창조의 삶으로의 전환을 위한 새로운 라이프 스타일을 제시합니다.

CV149

[2025-1] 박서형 - How far are we from solving the 2D & 3D Face Alignment problem? (and adataset of 230,000 3D facial landmarks) https://arxiv.org/abs/1703.07332 How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)This paper investigates how far a very deep neural network is from attaining close to saturating performance on existing 2D and 3D face alignment datasets. To this end, we make the following 5 contributions: (a) we construct, for the first time, a very st.. 2025. 4. 5.
[2025-1] 주서영 - Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance11institutetext: The University of Sydney Enabling Text-free Inference in Language-guided Segmentation of Chest X-rays via Self-guidance Shuchang Ye    Mingyuan Meng    Mingjian Li    Dagan Feng    Jinman Kim .. 2025. 4. 5.
[2025-1] 전연주 - Textmatch: Using Text Prompts to Improve Semisupervised Medical Image Segmentation 논문 링크: [2412.18185] TextMatch: Enhancing Image-Text Consistency Through Multimodal Optimization TextMatch: Enhancing Image-Text Consistency Through Multimodal OptimizationText-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal o.. 2025. 4. 4.
[2025-1] 최민서 - Score-based Generative Modeling through Stochastic Differential Equations [논문링크] https://arxiv.org/abs/2011.13456 Score-Based Generative Modeling through Stochastic Differential EquationsCreating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a correarxiv.orgSMLD와 DDPM 논문을 읽지 않았.. 2025. 4. 4.