78 papers with code • 8 benchmarks • 7 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
These leaderboards are used to track progress in Image Matting
LibrariesUse these libraries to find Image Matting models and implementations
Most implemented papers
Deep Image Matting
We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images.
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
MODNet is easy to be trained in an end-to-end manner.
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
With the help of novel masks or scenes, we enhance the current datasets using synthesized shadow images.
Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos
This paper proposes a vision-based method for video sky replacement and harmonization, which can automatically generate realistic and dramatic sky backgrounds in videos with controllable styles.
Intra-frame Object Tracking by Deblatting
We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object.
Real-time deep hair matting on mobile devices
Augmented reality is an emerging technology in many application domains.
Semantic Human Matting
SHM is the first algorithm that learns to jointly fit both semantic information and high quality details with deep networks.
Towards Real-Time Automatic Portrait Matting on Mobile Devices
We tackle the problem of automatic portrait matting on mobile devices.
By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision.
Non-Causal Tracking by Deblatting
Tracking by Deblatting stands for solving an inverse problem of deblurring and image matting for tracking motion-blurred objects.