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 101150 of 225 papers

TitleStatusHype
PolarMatte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting0
Lightweight high-resolution Subject Matting in the Real World0
DiffusionMat: Alpha Matting as Sequential Refinement Learning0
Lightweight Portrait Matting via Regional Attention and Refinement0
EFormer: Enhanced Transformer towards Semantic-Contour Features of Foreground for Portraits Matting0
Training-Free Neural Matte Extraction for Visual Effects0
Color-aware Deep Temporal Backdrop Duplex Matting System0
Disentangled Pre-training for Image MattingCode0
NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects0
Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation0
Mask-Guided Matting in the Wild0
Privileged Prior Information Distillation for Image Matting0
FactorMatte: Redefining Video Matting for Re-Composition Tasks0
Lightweight Alpha Matting Network Using Distillation-Based Channel PruningCode0
Hierarchical and Progressive Image Matting0
Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting0
3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography0
3D Matting: A Soft Segmentation Method Applied in Computed Tomography0
SGM-Net: Semantic Guided Matting Net0
SHDM-NET: Heat Map Detail Guidance with Image Matting for Industrial Weld Semantic Segmentation Network0
Layered Depth Refinement with Mask Guidance0
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation0
Resnet18 Model With Sequential Layer For Computing Accuracy On Image Classification Dataset0
AugStatic - A Light-Weight Image Augmentation LibraryCode0
Augmented Balanced Image Dataset Generator Using AugStatic LibraryCode0
Augmentation Techniques Analysis with Removal of Class Imbalance Using PyTorch for Intel Scene Dataset0
PP-Matting: High-Accuracy Natural Image MattingCode0
Situational Perception Guided Image Matting0
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
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation0
Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks0
Highly Efficient Natural Image Matting0
Multipath CNN with alpha matte inference for knee tissue segmentation from MRI0
MODNet-V: Improving Portrait Video Matting via Background RestorationCode0
Temporally Coherent Person Matting Trained on Fake-Motion Dataset0
Automatic Portrait Video Matting via Context Motion Network0
SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting0
A Generative Adversarial Framework for Optimizing Image Matting and Harmonization Simultaneously0
Fristograms: Revealing and Exploiting Light Field Internals0
SOLO: A Simple Framework for Instance Segmentation0
Prior-Induced Information Alignment for Image Matting0
Alpha Matte Generation from Single Input for Portrait Matting0
Cascade Image Matting with Deformable Graph Refinement0
Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention0
Smart Scribbles for Image Mating0
Foreground color prediction through inverse compositing0
Salient Image Matting0
Show:102550
← PrevPage 3 of 5Next →

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