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/foamliu/deep-image-matting-pytorch
https://github.com/hmchuong/MaGGIe
https://github.com/huggingface/transformers
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
https://github.com/huochaitiantang/pytorch-fast-matting-portrait
https://github.com/hyperconnect/MMNet
Towards Real-Time Automatic Portrait Matting on Mobile Devices
https://github.com/jm12138/SkyAR_Paddle_GUI
Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos
https://github.com/jtiger958/hair-segmentation-pytorch
https://github.com/kuangzijian/Flow-Based-Video-Matting
https://github.com/lizhengwei1992/Semantic_Human_Matting
https://github.com/lucaspk512/vrdone
https://github.com/marcoforte/fba_matting
https://github.com/mducducd/Shadow-Removal
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
https://github.com/mducducd/ghost-free-shadow-removal
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
https://github.com/mindspore-ai/models/tree/master/official/cv/semantic_human_matting
https://github.com/minus31/Portrait-segmentation
https://github.com/nachifur/DMTN
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
https://github.com/plemeri/transparent-background
https://github.com/poppinace/indexnet_matting
https://github.com/pwc-1/Paper-9/tree/main/1/vitmatte
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
https://github.com/pwc-1/Paper-9/tree/main/5/vitmatte
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
https://github.com/royshil/obs-backgroundremoval
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
https://github.com/rozumden/tbd3d
https://github.com/vietnamican/HAttMatting
https://github.com/woshiyyya/Auto-Retoucher-pytorch
Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing
https://github.com/yaksoy/AffinityBasedMattingToolbox
https://github.com/youngLBW/HRN
https://github.com/yunkezhang/FusionMatting
https://github.com/zackzhao1/BackgroundMattingV2-paddle
https://github.com/zhengpeng7/birefnet
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.