DFIMat: Decoupled Flexible Interactive Matting in Multi-person Scenarios
- 10 December 2024
- book chapter
- Published by Springer Nature
- p. 428-444
Abstract
No abstract availableKeywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Matte anything: Interactive natural image matting with segment anything modelImage and Vision Computing, 2024
- Bridging Composite and Real: Towards End-to-End Deep Image MattingInternational Journal of Computer Vision, 2022
- Mask Guided Matting via Progressive Refinement Network2021
- Improved Image Matting via Real-time User Clicks and Uncertainty Estimation2021
- Attention-Guided Hierarchical Structure Aggregation for Image Matting2020
- Boosting Semantic Human Matting With Coarse Annotations2020
- Learning-Based Sampling for Natural Image Matting2019
- A Late Fusion CNN for Digital Matting2019
- Deep Image Matting2017
- Improving Image Matting Using Comprehensive Sampling Sets2013