Image Matting
96 papers with code • 8 benchmarks • 8 datasets
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
Benchmarks
These leaderboards are used to track progress in Image Matting
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Image Matting models and implementationsDatasets
Composition-1K
AIM-500
Distinctions-646
P3M-10k
PPM-100
withoutbg100 dataset
Latest papers with no code
3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i. e., a soft mask, to describe lesions in a 3D medical image.
3D Matting: A Soft Segmentation Method Applied in Computed Tomography
It can be caused by many factors, such as the imaging properties, pathological anatomy, and the weak representation of the binary masks, which brings challenges to accurate 3D segmentation.
SGM-Net: Semantic Guided Matting Net
When the green screen is not available, the existing human matting methods need the help of additional inputs (such as trimap, background image, etc.
FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling
We consider the problem of task-agnostic feature upsampling in dense prediction where an upsampling operator is required to facilitate both region-sensitive tasks like semantic segmentation and detail-sensitive tasks such as image matting.
SHDM-NET: Heat Map Detail Guidance with Image Matting for Industrial Weld Semantic Segmentation Network
This paper proposes an industrial weld segmentation network based on a deep learning semantic segmentation algorithm fused with heatmap detail guidance and Image Matting to solve the automatic segmentation problem of weld regions.
Layered Depth Refinement with Mask Guidance
Depth maps are used in a wide range of applications from 3D rendering to 2D image effects such as Bokeh.
Resnet18 Model With Sequential Layer For Computing Accuracy On Image Classification Dataset
This paper highlights the addition of a sequential layer to the traditional RESNET 18 model for computing the accuracy of an Image classification dataset.
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation
The accuracies are acquired for each augmentation technique using a RESNET18 model.
Augmentation Techniques Analysis with Removal of Class Imbalance Using PyTorch for Intel Scene Dataset
A painful element of real data is that it tends to be imbalanced.
Situational Perception Guided Image Matting
In this paper, we propose a Situational Perception Guided Image Matting (SPG-IM) method that mitigates subjective bias of matting annotations and captures sufficient situational perception information for better global saliency distilled from the visual-to-textual task.
