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 76100 of 225 papers

TitleStatusHype
SGM-Net: Semantic Guided Matting Net0
Self-supervised Matting-specific Portrait Enhancement and GenerationCode1
TransMatting: Enhancing Transparent Objects Matting with TransformersCode1
One-Trimap Video MattingCode1
FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic UpsamplingCode1
SHDM-NET: Heat Map Detail Guidance with Image Matting for Industrial Weld Semantic Segmentation Network0
Referring Image MattingCode2
Layered Depth Refinement with Mask Guidance0
Human Instance Matting via Mutual Guidance and Multi-Instance RefinementCode1
Exploring the Interactive Guidance for Unified and Effective Image MattingCode1
AugStatic - A Light-Weight Image Augmentation LibraryCode0
Deep PCB To COCO ConvertorCode2
Augmented Balanced Image Dataset Generator Using AugStatic LibraryCode0
Augmentation Techniques Analysis with Removal of Class Imbalance Using PyTorch for Intel Scene Dataset0
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation0
Resnet18 Model With Sequential Layer For Computing Accuracy On Image Classification Dataset0
Exposure Correction Model to Enhance Image QualityCode1
PP-Matting: High-Accuracy Natural Image MattingCode0
Situational Perception Guided Image Matting0
Rethinking Portrait Matting with Privacy PreservingCode1
MatteFormer: Transformer-Based Image Matting via Prior-TokensCode2
Hybrid Mesh-neural Representation for 3D Transparent Object Reconstruction0
Attention based Memory video portrait matting0
Adaptive Background Matting Using Background Matching0
Efficient Video Segmentation Models with Per-frame Inference0
Show:102550
← PrevPage 4 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DIMMSE14Unverified
2IndexNet-MattingMSE13Unverified
3Context-Aware MattingMSE8.2Unverified
4SIMMSE5.8Unverified
5LSAMattingMSE5.4Unverified
6FBAMattingMSE5.3Unverified
7PP-MattingMSE5Unverified
8LFPNetMSE4.1Unverified
9MatteFormerMSE4Unverified
10TMFNetMSE3.6Unverified
#ModelMetricClaimedVerifiedStatus
1SHMCSAD61.5Unverified
2LFSAD36.12Unverified
3HATTSAD28.01Unverified
4SHMSAD17.81Unverified
5GFM(r)SAD10.89Unverified
6GFM(d)SAD10.26Unverified
7GFM(r2b)SAD10.24Unverified
8GFM(r')SAD9.66Unverified
9StyleMatteSAD9.6Unverified
#ModelMetricClaimedVerifiedStatus
1LFSAD42.95Unverified
2HATTSAD25.99Unverified
3SHMSAD21.56Unverified
4GFMSAD13.2Unverified
5P3M-Net (r)SAD8.73Unverified
6StyleMatteSAD6.97Unverified
7P3M-Net (v)SAD6.24Unverified
#ModelMetricClaimedVerifiedStatus
1LFSAD191.74Unverified
2SHMSAD170.44Unverified
3U2NETSAD83.46Unverified
4GFMSAD52.66Unverified
5AIM-NetSAD43.92Unverified
6DiffMatteSAD16.31Unverified
#ModelMetricClaimedVerifiedStatus
1CAMMSE4.5Unverified
2BMMSE1.33Unverified
3IMMSE1.16Unverified
4Adobe LS-GANMSE0.97Unverified
#ModelMetricClaimedVerifiedStatus
1PP-MattingSAD40.69Unverified
2DCAMSAD31.27Unverified
3ViTMatteSAD17.05Unverified
4DiffMatteSAD15.5Unverified
#ModelMetricClaimedVerifiedStatus
1MODNet+MAD0.81Unverified
#ModelMetricClaimedVerifiedStatus
1MODNet+ (Our)MAD0.97Unverified