Papers › Background Matting: The World is Your Green Screen

Background Matting: The World is Your Green Screen

1 Apr 2020CVPR 2020 6arXiv:2004.00626archive 2025-07-28

Soumyadip Sengupta, Vivek Jayaram, Brian Curless, Steve Seitz, Ira Kemelmacher-Shlizerman

We propose a method for creating a matte -- the per-pixel foreground color and alpha -- of a person by taking photos or videos in an everyday setting with a handheld camera. Most existing matting methods require a green screen background or a manually created trimap to produce a good matte. Automatic, trimap-free methods are appearing, but are not of comparable quality. In our trimap free approach, we ask the user to take an additional photo of the background without the subject at the time of capture. This step requires a small amount of foresight but is far less time-consuming than creating a trimap. We train a deep network with an adversarial loss to predict the matte. We first train a matting network with supervised loss on ground truth data with synthetic composites. To bridge the domain gap to real imagery with no labeling, we train another matting network guided by the first network and by a discriminator that judges the quality of composites. We demonstrate results on a wide variety of photos and videos and show significant improvement over the state of the art.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

senguptaumd/Background-Matting officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Matting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Matting Adobe Matting Adobe LS-GAN MSE 0.97 #1 of 4 Archive leaderboard report
Image Matting Adobe Matting Adobe LS-GAN SAD 1.72 #1 of 4 Archive leaderboard report
Image Matting Adobe Matting IM MSE 1.16 #2 of 4 Archive leaderboard report
Image Matting Adobe Matting IM SAD 1.92 #2 of 4 Archive leaderboard report
Image Matting Adobe Matting BM MSE 1.33 #3 of 4 Archive leaderboard report
Image Matting Adobe Matting BM SAD 2.53 #3 of 4 Archive leaderboard report
Image Matting Adobe Matting CAM MSE 4.5 #4 of 4 Archive leaderboard report
Image Matting Adobe Matting CAM SAD 3.67 #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections