mlsanityData to 14 Oct 2026

Mask Guided Matting via Progressive Refinement Network

arXiv 2012.06722 ↗First posted 12 Dec 2020cs.CVcited by 84

Not on the map. Why?

Abstract (arXiv)

We propose Mask Guided (MG) Matting, a robust matting framework that takes a general coarse mask as guidance. MG Matting leverages a network (PRN) design which encourages the matting model to provide self-guidance to progressively refine the uncertain regions through the decoding process. A series of guidance mask perturbation operations are also introduced in the training to further enhance its robustness to external guidance. We show that PRN can generalize to unseen types of guidance masks such as trimap and low-quality alpha matte, making it suitable for various application pipelines. In addition, we revisit the foreground color prediction problem for matting and propose a surprisingly simple improvement to address the dataset issue. Evaluation on real and synthetic benchmarks shows that MG Matting achieves state-of-the-art performance using various types of guidance inputs. Code and models are available at https://github.com/yucornetto/MGMatting.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 18; 2023: 19; 2024: 18; 2025: 12; 2026: 10.

84 papers.

Sort:

By area:

  1. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  2. 2021Privacy-Preserving Portrait Mattingcited by 60
  3. 2023Relightful Harmonization: Lighting-aware Portrait Background Replacementcited by 57
  4. 2023ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformerscited by 56
  5. 2022MatteFormer: Transformer-Based Image Matting via Prior-Tokenscited by 48
  6. 2022Self-Supervised Masking for Unsupervised Anomaly Detection and Localizationcited by 43
  7. 2023Matte Anything: Interactive Natural Image Matting with Segment Anything Modelscited by 39
  8. 2024MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generationcited by 38
  9. 2023Text2Layer: Layered Image Generation using Latent Diffusion Modelcited by 37
  10. 2021High Quality Segmentation for Ultra High-resolution Imagescited by 31
  11. 2023Matting Anythingcited by 31
  12. 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Processcited by 29
38 more
  1. 2021Attention-guided Temporally Coherent Video Object Mattingcited by 25
  2. 2022Rethinking Portrait Matting with Privacy Preservingcited by 25
  3. 2022Human Instance Matting via Mutual Guidance and Multi-Instance Refinementcited by 25
  4. 2021Wavelength-based Attributed Deep Neural Network for Underwater Image Restorationcited by 23
  5. 2022Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentationcited by 22
  6. 2022Referring Image Mattingcited by 22
  7. 2022VMFormer: End-to-End Video Matting with Transformercited by 20
  8. 2024MaGGIe: Masked Guided Gradual Human Instance Mattingcited by 18
  9. 2023Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentationcited by 17
  10. 2024ZIM: Zero-Shot Image Matting for Anythingcited by 16
  11. 2022TransMatting: Enhancing Transparent Objects Matting with Transformerscited by 15
  12. 2024Generating Compositional Scenes via Text-to-image RGBA Instance Generationcited by 14
  13. 2024Matting by Generationcited by 13
  14. 2022One-Trimap Video Mattingcited by 12
  15. 2022Robust Human Matting via Semantic Guidancecited by 12
  16. 2023Deep Image Matting: A Comprehensive Surveycited by 12
  17. 2021Cascade Image Matting with Deformable Graph Refinementcited by 11
  18. 2023Diffusion for Natural Image Mattingcited by 11
  19. 2025Consistent Image Layout Editing with Diffusion Modelscited by 9
  20. 2025AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learningcited by 8
  21. 2023Adaptive Human Matting for Dynamic Videoscited by 7
  22. 2025Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learnercited by 7
  23. 2022Exposure Correction Model to Enhance Image Qualitycited by 6
  24. 2023Revisiting Context Aggregation for Image Mattingcited by 5
  25. 2023TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localizationcited by 5
  26. 2022Hierarchical and Progressive Image Mattingcited by 4
  27. 2023Adversarially-Guided Portrait Mattingcited by 4
  28. 2023dugMatting: Decomposed-Uncertainty-Guided Mattingcited by 4
  29. 2023Video Instance Mattingcited by 4
  30. 2023Progressive Feedback-Enhanced Transformer for Image Forgery Localizationcited by 4
  31. 2024End-to-End Human Instance Mattingcited by 4
  32. 2024Boosting General Trimap-free Matting in the Real-World Imagecited by 4
  33. 2024Training Matting Models without Alpha Labelscited by 4
  34. 2025SDMatte: Grafting Diffusion Models for Interactive Mattingcited by 4
  35. 2026VideoMaMa: Mask-Guided Video Matting via Generative Priorcited by 4
  36. 2021Alpha Matte Generation from Single Input for Portrait Mattingcited by 3
  37. 2022Situational Perception Guided Image Mattingcited by 3
  38. 2024In-Context Mattingcited by 3

50 most cited of 84 All 84 (JSON)