mlsanityData to 14 Oct 2026

Matting Anything

arXiv 2306.05399 ↗First posted 8 Jun 2023cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

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. MAM offers several significant advantages over previous specialized image matting networks: (i) MAM is capable of dealing with various types of image matting, including semantic, instance, and referring image matting with only a single model; (ii) MAM leverages the feature maps from the Segment Anything Model (SAM) and adopts a lightweight Mask-to-Matte (M2M) module to predict the alpha matte through iterative refinement, which has only 2.7 million trainable parameters. (iii) By incorporating SAM, MAM simplifies the user intervention required for the interactive use of image matting from the trimap to the box, point, or text prompt. We evaluate the performance of MAM on various image matting benchmarks, and the experimental results demonstrate that MAM achieves comparable performance to the state-of-the-art specialized image matting models under different metrics on each benchmark. Overall, MAM shows superior generalization ability and can effectively handle various image matting tasks with fewer parameters, making it a practical solution for unified image matting. Our code and models are open-sourced at https://github.com/SHI-Labs/Matting-Anything.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 44 of its 59 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

44 of 59 references.

References · 44

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2023Segment Anythingcited by 8,234
  3. 2017Mask R-CNNcited by 7,277
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  7. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 819
  8. 2018Self-Attention Generative Adversarial Networkscited by 809
  9. 2018Panoptic Segmentationcited by 802
  10. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  11. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 531
  12. 2021Image Segmentation Using Text and Image Promptscited by 512
32 more
  1. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  2. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 328
  3. 2022Neighborhood Attention Transformercited by 239
  4. 2017Deep Image Mattingcited by 150
  5. 2021Robust High-Resolution Video Matting with Temporal Guidancecited by 137
  6. 2020MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decompositioncited by 127
  7. 2020CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinementcited by 113
  8. 2020Background Matting: The World is Your Green Screencited by 105
  9. 2020Bridging Composite and Real: Towards End-to-end Deep Image Mattingcited by 89
  10. 2020Mask Guided Matting via Progressive Refinement Networkcited by 84
  11. 2019Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimationcited by 79
  12. 2020Natural Image Matting via Guided Contextual Attentioncited by 78
  13. 2018Semantic Human Mattingcited by 67
  14. 2017Information-Flow Mattingcited by 59
  15. 2021Deep Automatic Natural Image Mattingcited by 59
  16. 2021Semantic Image Mattingcited by 55
  17. 2021SeMask: Semantically Masked Transformers for Semantic Segmentationcited by 55
  18. 2020F, B, Alpha Mattingcited by 50
  19. 2020Boosting Semantic Human Matting with Coarse Annotationscited by 48
  20. 2022MatteFormer: Transformer-Based Image Matting via Prior-Tokenscited by 48
  21. 2021Deep Video Matting via Spatio-Temporal Alignment and Aggregationcited by 41
  22. 2023Matte Anything: Interactive Natural Image Matting with Segment Anything Modelscited by 39
  23. 2020High-Resolution Deep Image Mattingcited by 36
  24. 2017Fast Deep Matting for Portrait Animation on Mobile Phonecited by 30
  25. 2022Human Instance Matting via Mutual Guidance and Multi-Instance Refinementcited by 25
  26. 2020Improved Image Matting via Real-time User Clicks and Uncertainty Estimationcited by 22
  27. 2022Referring Image Mattingcited by 22
  28. 2022VMFormer: End-to-End Video Matting with Transformercited by 20
  29. 2023LMSeg: Language-guided Multi-dataset Segmentationcited by 15
  30. 2023Deep Image Matting: A Comprehensive Surveycited by 12
  31. 2021MODNet-V: Improving Portrait Video Matting via Background Restorationcited by 7
  32. 2022Situational Perception Guided Image Mattingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 16; 2026: 5.

31 papers.

Sort:

By area:

  1. 2025Qwen-Image-Layered: Towards Inherent Editability via Layer Decompositioncited by 34
  2. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  3. 2025TransAnimate: Taming Layer Diffusion to Generate RGBA Videocited by 24
  4. 2023Polyp-SAM++: Can A Text Guided SAM Perform Better for Polyp Segmentation?cited by 22
  5. 2024LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priorscited by 19
  6. 2024ZIM: Zero-Shot Image Matting for Anythingcited by 16
  7. 2025OmniPSD: Layered PSD Generation with Diffusion Transformercited by 13
  8. 2025TransPixeler: Advancing Text-to-Video Generation with Transparencycited by 12
  9. 2025PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignmentcited by 12
  10. 2023Diffusion for Natural Image Mattingcited by 11
  11. 2025Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesiscited by 10
  12. 2025Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpaintingcited by 5
19 more
  1. 2025Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceiverscited by 5
  2. 2023Video Instance Mattingcited by 4
  3. 2025SDMatte: Grafting Diffusion Models for Interactive Mattingcited by 4
  4. 2025From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decompositioncited by 4
  5. 2024In-Context Mattingcited by 3
  6. 2024Learning Trimaps via Clicks for Image Mattingcited by 3
  7. 2024Towards Natural Image Matting in the Wild via Real-Scenario Priorcited by 3
  8. 2024ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillationcited by 2
  9. 2025Object-Aware Video Matting with Cross-Frame Guidancecited by 2
  10. 2025VRMDiff: Text-Guided Video Referring Matting Generation of Diffusioncited by 2
  11. 2025InfSplign: Inference-Time Spatial Alignment of Text-to-Image Diffusion Modelscited by 1
  12. 2025Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentationcited by 0
  13. 2025FocalClick-XL: Towards Unified and High-quality Interactive Segmentationcited by 0
  14. 2025Capture Stage Matting: Challenges, Approaches, and Solutions for Offline and Real-Time Processingcited by 0
  15. 2026ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysiscited by 0
  16. 2026αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversioncited by 0
  17. 2026SAM2Matting: Generalized Image and Video Mattingcited by 0
  18. 2026Parallax Portrait Mattingcited by 0
  19. 2026Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generationcited by 0