mlsanityData to 14 Oct 2026

Deep Image Matting

arXiv 1703.03872 ↗First posted 10 Mar 2017cs.CVcited by 150

Not on the map. Why?

Abstract (arXiv)

Image matting is a fundamental computer vision problem and has many applications. Previous algorithms have poor performance when an image has similar foreground and background colors or complicated textures. The main reasons are prior methods 1) only use low-level features and 2) lack high-level context. In this paper, we propose a novel deep learning based algorithm that can tackle both these problems. Our deep model has two parts. The first part is a deep convolutional encoder-decoder network that takes an image and the corresponding trimap as inputs and predict the alpha matte of the image. The second part is a small convolutional network that refines the alpha matte predictions of the first network to have more accurate alpha values and sharper edges. In addition, we also create a large-scale image matting dataset including 49300 training images and 1000 testing images. We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images. Experimental results clearly demonstrate the superiority of our algorithm over previous methods.

Key facts. Cited by 150 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 35; 2022: 33; 2023: 23; 2024: 28; 2025: 20; 2026: 11.

150 papers.

Sort:

By area:

  1. 2021Concealed Object Detectioncited by 212
  2. 2021Robust High-Resolution Video Matting with Temporal Guidancecited by 137
  3. 2024Transparent Image Layer Diffusion using Latent Transparencycited by 114
  4. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  5. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  6. 2022FocalClick: Towards Practical Interactive Image Segmentationcited by 102
  7. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
  8. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  9. 2021Deep Automatic Natural Image Mattingcited by 59
  10. 2023ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformerscited by 56
  11. 2021Semantic Image Mattingcited by 55
  12. 2021Omnimatte: Associating Objects and Their Effects in Videocited by 50
38 more
  1. 2022MatteFormer: Transformer-Based Image Matting via Prior-Tokenscited by 48
  2. 2022BokehMe: When Neural Rendering Meets Classical Renderingcited by 48
  3. 2021Boundary-Aware Segmentation Network for Mobile and Web Applicationscited by 42
  4. 2021Deep Video Matting via Spatio-Temporal Alignment and Aggregationcited by 41
  5. 2023Matte Anything: Interactive Natural Image Matting with Segment Anything Modelscited by 39
  6. 2024MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generationcited by 38
  7. 2023Text2Layer: Layered Image Generation using Latent Diffusion Modelcited by 37
  8. 2022ObjectStitch: Generative Object Compositingcited by 36
  9. 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
  10. 2022A Unified Query-based Paradigm for Point Cloud Understandingcited by 32
  11. 2022SAPA: Similarity-Aware Point Affiliation for Feature Upsamplingcited by 32
  12. 2023Matting Anythingcited by 31
  13. 2023LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentationcited by 29
  14. 2021Attention-guided Temporally Coherent Video Object Mattingcited by 25
  15. 2022Rethinking Portrait Matting with Privacy Preservingcited by 25
  16. 2022Human Instance Matting via Mutual Guidance and Multi-Instance Refinementcited by 25
  17. 2022FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsamplingcited by 25
  18. 2022PP-Matting: High-Accuracy Natural Image Mattingcited by 23
  19. 2022Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentationcited by 22
  20. 2022Referring Image Mattingcited by 22
  21. 2023Head-Free Lightweight Semantic Segmentation with Linear Transformercited by 22
  22. 2025LayerD: Decomposing Raster Graphic Designs into Layerscited by 21
  23. 2022VMFormer: End-to-End Video Matting with Transformercited by 20
  24. 2023InterFormer: Real-time Interactive Image Segmentationcited by 20
  25. 2024Alfie: Democratising RGBA Image Generation With No cited by 20
  26. 2025SAMRefiner: Taming Segment Anything Model for Universal Mask Refinementcited by 20
  27. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
  28. 2024MaGGIe: Masked Guided Gradual Human Instance Mattingcited by 18
  29. 2021Convolutional Neural Opacity Radiance Fieldscited by 16
  30. 2024ZIM: Zero-Shot Image Matting for Anythingcited by 16
  31. 2022TransMatting: Enhancing Transparent Objects Matting with Transformerscited by 15
  32. 2021IICNet: A Generic Framework for Reversible Image Conversioncited by 13
  33. 2021Long-Range Feature Propagating for Natural Image Mattingcited by 13
  34. 2024Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A surveycited by 13
  35. 2024DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotationcited by 13
  36. 2025OmniPSD: Layered PSD Generation with Diffusion Transformercited by 13
  37. 2021Towards Enhancing Fine-grained Details for Image Mattingcited by 12
  38. 2022One-Trimap Video Mattingcited by 12

50 most cited of 150 All 150 (JSON)