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.
AlphaNet: An Attention Guided Deep Network for Automatic Image Matting
Background Matting
Natural Image Matting via Guided Contextual Attention
Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
Colored Transparent Object Matting from a Single Image Using Deep Learning
Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation
Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision
Non-Causal Tracking by Deblatting
Disentangled Image Matting
Index Network
Indices Matter: Learning to Index for Deep Image Matting
Learning Transparent Object Matting
Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
Intra-frame Object Tracking by Deblatting
Patch alignment manifold matting
Instance Segmentation based Semantic Matting for Compositing Applications
Towards Real-Time Automatic Portrait Matting on Mobile Devices
U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans
a high efficiency fully convolutional networks for pixel wise surface defect detection
Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing
Fourier-Domain Optimization for Image Processing
Semantic Human Matting
Automatic Foreground Extraction from Imperfect Backgrounds using Multi-Agent Consensus Equilibrium
AlphaGAN: Generative adversarial networks for natural image matting
Deep-Energy: Unsupervised Training of Deep Neural Networks
Visual Object Tracking: The Initialisation Problem
TOM-Net: Learning Transparent Object Matting from a Single Image
Real-time deep hair matting on mobile devices
Image matting with normalized weight and semi-supervised learning
Learning Affinity via Spatial Propagation Networks
Fast Deep Matting for Portrait Animation on Mobile Phone
Information-Flow Matting
Automatic Trimap Generation for Image Matting
Deep Image Matting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.