Image Matting
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 8
- 보존된 평가 기록
- 45
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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/JizhiziLi/GFM
공식 코드Bridging Composite and Real: Towards End-to-end Deep Image Matting
https://github.com/JizhiziLi/P3M
공식 코드https://github.com/JuanLuisGonzalez/PLADE-net
공식 코드https://github.com/PaddlePaddle/PaddleSeg
공식 코드https://github.com/PeterL1n/BackgroundMattingV2
공식 코드https://github.com/PeterL1n/RobustVideoMatting
공식 코드https://github.com/PramaLLC/BEN
공식 코드BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation
https://github.com/Serge-weihao/TMF-Matting
공식 코드Trimap-guided Feature Mining and Fusion Network for Natural Image Matting
https://github.com/Yaoyi-Li/GCA-Matting
공식 코드https://github.com/ZHKKKe/MODNet
공식 코드MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
https://github.com/ZHKKKe/PPM
공식 코드MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
https://github.com/ZHKKKe/PixelSSL
공식 코드Guided Collaborative Training for Pixel-wise Semi-Supervised Learning
https://github.com/acechq/transmatting
공식 코드TransMatting: Enhancing Transparent Objects Matting with Transformers
https://github.com/aim-uofa/genpercept
공식 코드What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
https://github.com/aimagelab/alfie
공식 코드https://github.com/charch-630/fgi-matting
공식 코드https://github.com/chenyizhang007/click2trimap
공식 코드https://github.com/chroneus/stylematte
공식 코드https://github.com/cnnlstm/stylegan_matting
공식 코드Self-supervised Matting-specific Portrait Enhancement and Generation
https://github.com/coconuthust/composition_styles
공식 코드Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting
https://github.com/crystraldo/dpt
공식 코드https://github.com/cxgincsu/semanticguidedhumanmatting
공식 코드https://github.com/dinghow/uim
공식 코드Exploring the Interactive Guidance for Unified and Effective Image Matting
https://github.com/donggeun-yoon/dcp
공식 코드Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning
https://github.com/duembgen/fourier-deconv
공식 코드https://github.com/facebookresearch/OmnimatteRF
공식 코드https://github.com/fire-friend/dugmatting
공식 코드https://github.com/georgedeath/initialisation-problem
공식 코드https://github.com/guanyingc/TOM-Net
공식 코드TOM-Net: Learning Transparent Object Matting from a Single Image
https://github.com/guanyingc/TOM-Net_Rendering
공식 코드https://github.com/hansxsourse/vrmdiff
공식 코드VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
https://github.com/hongje/otvm
공식 코드https://github.com/hqqxyy/Context-Aware-Matting
공식 코드Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation
https://github.com/hustvl/ViTMatte
공식 코드ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
https://github.com/hustvl/matte-anything
공식 코드Matte Anything: Interactive Natural Image Matting with Segment Anything Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.