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

Libraries

Use these libraries to find Image Matting models and implementations

Learning Trimaps via Clicks for Image Matting

chenyizhang007/click2trimap 30 Mar 2024

Despite significant advancements in image matting, existing models heavily depend on manually-drawn trimaps for accurate results in natural image scenarios.

5
30 Mar 2024

In-Context Matting

tiny-smart/in-context-matting 23 Mar 2024

We introduce in-context matting, a novel task setting of image matting.

14
23 Mar 2024

End-to-End Human Instance Matting

qlyoo/e2e-him 3 Mar 2024

Finally, an instance matting network decodes the image features and united semantics guidance to predict all instance-level alpha mattes.

8
03 Mar 2024

Dual-Context Aggregation for Universal Image Matting

windaway/dcam 28 Feb 2024

However, existing matting methods are designed for specific objects or guidance, neglecting the common requirement of aggregating global and local contexts in image matting.

3
28 Feb 2024

Diffusion for Natural Image Matting

yihanhu-2022/diffmatte 10 Dec 2023

However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles to achieving this goal.

44
10 Dec 2023

Video Instance Matting

shi-labs/vim 7 Nov 2023

To remedy this deficiency, we propose Video Instance Matting~(VIM), that is, estimating alpha mattes of each instance at each frame of a video sequence.

49
07 Nov 2023

OmnimatteRF: Robust Omnimatte with 3D Background Modeling

facebookresearch/OmnimatteRF ICCV 2023

Video matting has broad applications, from adding interesting effects to casually captured movies to assisting video production professionals.

117
14 Sep 2023

On Point Affiliation in Feature Upsampling

poppinace/sapa 17 Jul 2023

We introduce the notion of point affiliation into feature upsampling.

33
17 Jul 2023

Matting Anything

shi-labs/matting-anything 8 Jun 2023

In this paper, we propose the Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance.

532
08 Jun 2023

Matte Anything: Interactive Natural Image Matting with Segment Anything Models

hustvl/matte-anything 7 Jun 2023

In our work, we leverage vision foundation models to enhance the performance of natural image matting.

402
07 Jun 2023