https://github.com/wangsssky/MedicalMatting
공식 코드Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Image Matting is the process of accurately estimating the foreground object in images and videos. It is a very important technique in image and video editing applications, particularly in film production for creating visual effects. In case of image segmentation, we segment the image into foreground and background by labeling the pixels. Image segmentation generates a binary image, in which a pixel either belongs to foreground or background. However, Image Matting is different from the image segmentation, wherein some pixels may belong to foreground as well as background, such pixels are called partial or mixed pixels. In order to fully separate the foreground from the background in an image, accurate estimation of the alpha values for partial or mixed pixels is necessary.
Source: Automatic Trimap Generation for Image Matting
Image Source: Real-Time High-Resolution Background Matting
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
MatteFormer: Transformer-Based Image Matting via Prior-Tokens
Towards Natural Image Matting in the Wild via Real-Scenario Prior
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos
AlphaGAN: Generative adversarial networks for natural image matting
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
MODNet-V: Improving Portrait Video Matting via Background Restoration
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
TOM-Net: Learning Transparent Object Matting from a Single Image
TOM-Net: Learning Transparent Object Matting from a Single Image
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.