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.
Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
Alpha Matte Generation from Single Input for Portrait Matting
Attention-guided Temporally Coherent Video Object Matting
Cascade Image Matting with Deformable Graph Refinement
Privacy-Preserving Portrait Matting
Deep Video Matting via Spatio-Temporal Alignment and Aggregation
Flow-based Video Segmentation for Human Head and Shoulders
Semantic Image Matting
Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention
Smart Scribbles for Image Mating
Foreground color prediction through inverse compositing
Salient Image Matting
PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss
Towards Enhancing Fine-grained Details for Image Matting
Multi-scale Information Assembly for Image Matting
FMODetect: Robust Detection of Fast Moving Objects
Improved Image Matting via Real-time User Clicks and Uncertainty Estimation
Real-Time High-Resolution Background Matting
Mask Guided Matting via Progressive Refinement Network
Learning Affinity-Aware Upsampling for Deep Image Matting
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
Deep Image Compositing
Bridging Composite and Real: Towards End-to-end Deep Image Matting
Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos
High-Resolution Deep Image Matting
Guided Collaborative Training for Pixel-wise Semi-Supervised Learning
Complex Network Construction for Interactive Image Segmentation using Particle Competition and Cooperation: A New Approach
Fast Multi-Level Foreground Estimation
An Advert Creation System for 3D Product Placements
JIT-Masker: Efficient Online Distillation for Background Matting
GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
Boosting Semantic Human Matting with Coarse Annotations
Hierarchical Opacity Propagation for Image Matting
Background Matting: The World is Your Green Screen
PyMatting: A Python Library for Alpha Matting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.