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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
One-Trimap Video Matting
FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling
SHDM-NET: Heat Map Detail Guidance with Image Matting for Industrial Weld Semantic Segmentation Network
Referring Image Matting
Layered Depth Refinement with Mask Guidance
Human Instance Matting via Mutual Guidance and Multi-Instance Refinement
Exploring the Interactive Guidance for Unified and Effective Image Matting
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation
Augmentation Techniques Analysis with Removal of Class Imbalance Using PyTorch for Intel Scene Dataset
Exposure Correction Model to Enhance Image Quality
Situational Perception Guided Image Matting
PP-Matting: High-Accuracy Natural Image Matting
Rethinking Portrait Matting with Privacy Preserving
MatteFormer: Transformer-Based Image Matting via Prior-Tokens
Hybrid Mesh-neural Representation for 3D Transparent Object Reconstruction
Attention based Memory video portrait matting
Adaptive Background Matting Using Background Matching
Efficient Video Segmentation Models with Per-frame Inference
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation
Improving Deep Image Matting via Local Smoothness Assumption
Trimap-guided Feature Mining and Fusion Network for Natural Image Matting
Highly Efficient Natural Image Matting
Deep Image Matting with Flexible Guidance Input
Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction
Multipath CNN with alpha matte inference for knee tissue segmentation from MRI
Long-Range Feature Propagating for Natural Image Matting
MODNet-V: Improving Portrait Video Matting via Background Restoration
Automatic Portrait Video Matting via Context Motion Network
Temporally Coherent Person Matting Trained on Fake-Motion Dataset
SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting
Robust High-Resolution Video Matting with Temporal Guidance
A Generative Adversarial Framework for Optimizing Image Matting and Harmonization Simultaneously
Fristograms: Revealing and Exploiting Light Field Internals
Deep Automatic Natural Image Matting
SOLO: A Simple Framework for Instance Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.