Real-Time High-Resolution Background Matting
Shanchuan Lin, Andrey Ryabtsev, Soumyadip Sengupta, Brian L. Curless, Steven M. Seitz, Ira Kemelmacher-Shlizerman
Abstract
Zoom input and background shot Zoom with new background Our Zoom plugin with new background Figure 1: Current video conferencing tools like Zoom can take an input feed (left) and replace the background, often introducing artifacts, as shown in the center result with close-ups of hair and glasses that still have the residual of the original background. Leveraging a frame of video without the subject (far left inset), our method produces real-time, high-resolution background matting without those common artifacts. The image on the right is our result with the corresponding close-ups, screenshot from our Zoom plugin implementation.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 1c8832b2-b1e5-4102-b3af-62579d892e59Cited by top-tier papers90
- Total relighting: learning to relight portraits for background replacementRohit Pandey, Sergio Orts-Escolano, Chloe LeGendre, Christian Häne et al.SIGGRAPH 2021 · 138 citations
- DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric RenderingWei Cheng, Ruixiang Chen, Siming Fan, Wanqi Yin et al.ICCV 2023 · 106 citations
- NeRSemble: Multi-view Radiance Field Reconstruction of Human HeadsTobias Kirschstein, Shenhan Qian, Simon Giebenhain, Tim Walter et al.SIGGRAPH 2023 · 106 citations
- Gaussian Head Avatar: Ultra High-Fidelity Head Avatar via Dynamic GaussiansYuelang Xu, Bengwang Chen, Zhe Li, Hongwen Zhang et al.CVPR 2024 · 84 citations
- MatteFormer: Transformer-Based Image Matting via Prior-TokensGyutae Park, Sungjoon Son, Jaeyoung Yoo, Seho Kim et al.CVPR 2022 · 82 citations
Builds on5
- Indices Matter: Learning to Index for Deep Image MattingHao Lu, Yutong Dai, Chunhua Shen, Songcen XuICCV 2019 · 206 citations
- Context-Aware Image Matting for Simultaneous Foreground and Alpha EstimationQiqi Hou, Feng LiuICCV 2019 · 171 citations
- Boosting Semantic Human Matting With Coarse AnnotationsJinlin Liu, Yuan Yao, Wendi Hou, Miaomiao Cui et al.CVPR 2020
- Attention-Guided Hierarchical Structure Aggregation for Image MattingYu Qiao, Yuhao Liu, Xin Yang, Dongsheng Zhou et al.CVPR 2020
- Background Matting: The World Is Your Green ScreenSoumyadip Sengupta, Vivek Jayaram, Brian Curless, Steven M. Seitz et al.CVPR 2020
Related papers
- Seeing Through: Analyzing and Attacking Virtual Backgrounds in Video CallsFelix Weissberg, Jan Malte Hilgefort, Steve Grogorick, Daniel Arp et al.USENIX Security 2025
- Polarized Color Screen MattingKenji Enomoto, Scott Cohen, Brian L. Price, T. J. RhodesCVPR 2025
- Generative Omnimatte: Learning to Decompose Video into LayersYao-Chih Lee, Erika Lu, Sarah Rumbley, Michal Geyer et al.CVPR 2025
- OmnimatteRF: Robust Omnimatte with 3D Background ModelingGeng Lin, Chen Gao, Jia-Bin Huang, Changil Kim et al.ICCV 2023 · 17 citations
- Blind Video Deflickering by Neural Filtering with a Flawed AtlasChenyang Lei, Xuanchi Ren, Zhaoxiang Zhang, Qifeng ChenCVPR 2023
