SGM-Net: Semantic Guided Matting Net
Not on the map. Why?
Abstract (arXiv)
Human matting refers to extracting human parts from natural images with high quality, including human detail information such as hair, glasses, hat, etc. This technology plays an essential role in image synthesis and visual effects in the film industry. When the green screen is not available, the existing human matting methods need the help of additional inputs (such as trimap, background image, etc.), or the model with high computational cost and complex network structure, which brings great difficulties to the application of human matting in practice. To alleviate such problems, most existing methods (such as MODNet) use multi-branches to pave the way for matting through segmentation, but these methods do not make full use of the image features and only utilize the prediction results of the network as guidance information. Therefore, we propose a module to generate foreground probability map and add it to MODNet to obtain Semantic Guided Matting Net (SGM-Net). Under the condition of only one image, we can realize the human matting task. We verify our method on the P3M-10k dataset. Compared with the benchmark, our method has significantly improved in various evaluation indicators.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 16 Aug 2022.
Builds on
24 of 47 references.
References · 24
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2020Image Segmentation Using Deep Learning: A Surveycited by 660
- 2020Real-Time High-Resolution Background Mattingcited by 173
- 2017Deep Image Mattingcited by 150
- 2021Robust High-Resolution Video Matting with Temporal Guidancecited by 137
- 2019An Attentive Survey of Attention Modelscited by 124
- 2020Background Matting: The World is Your Green Screencited by 105
- 2019Indices Matter: Learning to Index for Deep Image Mattingcited by 93
- 2020Bridging Composite and Real: Towards End-to-end Deep Image Mattingcited by 89
- 2020Mask Guided Matting via Progressive Refinement Networkcited by 84
- 2019Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimationcited by 79
- 2020Natural Image Matting via Guided Contextual Attentioncited by 78
12 more
- 2018Semantic Human Mattingcited by 67
- 2021Privacy-Preserving Portrait Mattingcited by 60
- 2017Information-Flow Mattingcited by 59
- 2018Parsing R-CNN for Instance-Level Human Analysiscited by 53
- 2018AlphaGAN: Generative adversarial networks for natural image mattingcited by 50
- 2020Boosting Semantic Human Matting with Coarse Annotationscited by 48
- 2018Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Networkcited by 38
- 2020Renovating Parsing R-CNN for Accurate Multiple Human Parsingcited by 37
- 2022Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learningcited by 26
- 2021Quality-Aware Network for Human Parsingcited by 13
- 2017Automatic Trimap Generation for Image Mattingcited by 6
- 2021Salient Image Mattingcited by 6
Built on by
Citing papers per year: 2024: 1.
1 paper.