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 126–150 of 225 papers

TitleStatusHype
Augmentation Techniques Analysis with Removal of Class Imbalance Using PyTorch for Intel Scene Dataset—0
PP-Matting: High-Accuracy Natural Image Matting—0
Situational Perception Guided Image Matting—0
Hybrid Mesh-neural Representation for 3D Transparent Object Reconstruction—0
Attention based Memory video portrait matting—0
Adaptive Background Matting Using Background Matching—0
Efficient Video Segmentation Models with Per-frame Inference—0
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation—0
Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks—0
Highly Efficient Natural Image Matting—0
Multipath CNN with alpha matte inference for knee tissue segmentation from MRI—0
MODNet-V: Improving Portrait Video Matting via Background RestorationCode0
Temporally Coherent Person Matting Trained on Fake-Motion Dataset—0
Automatic Portrait Video Matting via Context Motion Network—0
SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting—0
A Generative Adversarial Framework for Optimizing Image Matting and Harmonization Simultaneously—0
Fristograms: Revealing and Exploiting Light Field Internals—0
SOLO: A Simple Framework for Instance Segmentation—0
Prior-Induced Information Alignment for Image Matting—0
Alpha Matte Generation from Single Input for Portrait Matting—0
Cascade Image Matting with Deformable Graph Refinement—0
Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention—0
Smart Scribbles for Image Mating—0
Foreground color prediction through inverse compositing—0
Salient Image Matting—0
Show:102550
← PrevPage 6 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