SOTAVerified

Image Matting

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

Papers

Showing 151–175 of 225 papers

TitleStatusHype
PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting LossCode0
Towards Enhancing Fine-grained Details for Image Matting—0
Multi-scale Information Assembly for Image Matting—0
Video Matting via Consistency-Regularized Graph Neural Networks—0
Improved Image Matting via Real-time User Clicks and Uncertainty Estimation—0
Deep Image Compositing—0
Attention Transfer Network for Nature Image MattingCode0
High-Resolution Deep Image Matting—0
Guided Collaborative Training for Pixel-wise Semi-Supervised Learning—0
Complex Network Construction for Interactive Image Segmentation using Particle Competition and Cooperation: A New Approach—0
An Advert Creation System for 3D Product Placements—0
GIMP-ML: Python Plugins for using Computer Vision Models in GIMP—0
JMNet: A joint matting network for automatic human matting—0
Hierarchical Opacity Propagation for Image Matting—0
AlphaNet: An Attention Guided Deep Network for Automatic Image Matting—0
Background Matting—0
Sub-frame Appearance and 6D Pose Estimation of Fast Moving ObjectsCode0
Colored Transparent Object Matting from a Single Image Using Deep Learning—0
Generative Adversarial Training for Weakly Supervised Cloud Matting—0
Context-Aware Image Matting for Simultaneous Foreground and Alpha EstimationCode0
Deeply Matting-based Dual Generative Adversarial Network for Image and Document Label Supervision—0
Non-Causal Tracking by DeblattingCode0
Disentangled Image Matting—0
Index NetworkCode0
Indices Matter: Learning to Index for Deep Image MattingCode0
Show:102550
← PrevPage 7 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DIMMSE14—Unverified
2IndexNet-MattingMSE13—Unverified
3Context-Aware MattingMSE8.2—Unverified
4SIMMSE5.8—Unverified
5LSAMattingMSE5.4—Unverified
6FBAMattingMSE5.3—Unverified
7PP-MattingMSE5—Unverified
8LFPNetMSE4.1—Unverified
9MatteFormerMSE4—Unverified
10TMFNetMSE3.6—Unverified
#ModelMetricClaimedVerifiedStatus
1SHMCSAD61.5—Unverified
2LFSAD36.12—Unverified
3HATTSAD28.01—Unverified
4SHMSAD17.81—Unverified
5GFM(r)SAD10.89—Unverified
6GFM(d)SAD10.26—Unverified
7GFM(r2b)SAD10.24—Unverified
8GFM(r')SAD9.66—Unverified
9StyleMatteSAD9.6—Unverified
#ModelMetricClaimedVerifiedStatus
1LFSAD42.95—Unverified
2HATTSAD25.99—Unverified
3SHMSAD21.56—Unverified
4GFMSAD13.2—Unverified
5P3M-Net (r)SAD8.73—Unverified
6StyleMatteSAD6.97—Unverified
7P3M-Net (v)SAD6.24—Unverified
#ModelMetricClaimedVerifiedStatus
1LFSAD191.74—Unverified
2SHMSAD170.44—Unverified
3U2NETSAD83.46—Unverified
4GFMSAD52.66—Unverified
5AIM-NetSAD43.92—Unverified
6DiffMatteSAD16.31—Unverified
#ModelMetricClaimedVerifiedStatus
1CAMMSE4.5—Unverified
2BMMSE1.33—Unverified
3IMMSE1.16—Unverified
4Adobe LS-GANMSE0.97—Unverified
#ModelMetricClaimedVerifiedStatus
1PP-MattingSAD40.69—Unverified
2DCAMSAD31.27—Unverified
3ViTMatteSAD17.05—Unverified
4DiffMatteSAD15.5—Unverified
#ModelMetricClaimedVerifiedStatus
1MODNet+MAD0.81—Unverified
#ModelMetricClaimedVerifiedStatus
1MODNet+ (Our)MAD0.97—Unverified