3260 papers • 126 benchmarks • 313 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
(Image credit: Papersgraph)
These leaderboards are used to track progress in image-matting-8
Use these libraries to find image-matting-8 models and implementations
A light-weight matting objective decomposition network (MODNet) for portrait matting in real-time with a single input image that outperforms prior trimap-free methods by a large margin and achieves remarkable results on daily photos and videos.
A novel deep learning based algorithm that can tackle image matting problems when an image has similar foreground and background colors or complicated textures and evaluation results demonstrate the superiority of this algorithm over previous methods.
A shadow matting generative adversarial network (SMGAN) is designed to synthesize realistic shadow mattings from a given shadow mask and shadow-free image to outperforms other state-of-the-art methods by a large margin.
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 and can be well applied to either online or offline processing scenarios.
This work hypothesizes that image matting could also be boosted by ViTs and presents a new efficient and robust ViT-based matting system, named ViTMatte, which achieves state-of-the-art performance and outperforms prior matting works by a large margin.
This work proposes 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 and outperforms baseline both in recall and trajectory accuracy.
A modified MobileNet CNN architecture can be used to segment the hair in real-time, and it is shown how this network can produce accurate and fine-detailed hair mattes, while running at over 30 fps on an iPad Pro tablet.
Semantic Human Matting (SHM) is the first algorithm that learns to jointly fit both semantic information and high quality details with deep networks and achieves comparable results with state-of-the-art interactive matting methods.
The model MMNet, based on multi-branch dilated convolution with linear bottleneck blocks, outperforms the state-of-the-art model and is orders of magnitude faster than Mobile DeepLabv3 while maintaining comparable performance.
Adding a benchmark result helps the community track progress.