TY - GEN
T1 - Alpha Matte Generation from Single Input for Portrait Matting
AU - Yaman, Dogucan
AU - Ekenel, Hazim Kemal
AU - Waibel, Alexander
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In the portrait matting, the goal is to predict an alpha matte that identifies the effect of each pixel on the foreground subject. Traditional approaches and most of the existing works utilized an additional input, e.g., trimap, background image, to predict alpha matte. However, (1) providing additional input is not always practical, and (2) models are too sensitive to these additional inputs. To address these points, in this paper, we introduce an additional input-free approach to perform portrait matting. We divide the task into two subtasks, segmentation and alpha matte prediction. We first generate a coarse segmentation map from the input image and then predict the alpha matte by utilizing the image and segmentation map. Besides, we present a segmentation encoding block to downsample the coarse segmentation map and provide useful feature representation to the residual block, since using a single encoder causes the vanishing of the segmentation information. We tested our model on four different benchmark datasets. The proposed method outperformed the MODNet and MGMatting methods that also take a single input. Besides, we obtained comparable results with BGM-V2 and FBA methods that require additional input.
AB - In the portrait matting, the goal is to predict an alpha matte that identifies the effect of each pixel on the foreground subject. Traditional approaches and most of the existing works utilized an additional input, e.g., trimap, background image, to predict alpha matte. However, (1) providing additional input is not always practical, and (2) models are too sensitive to these additional inputs. To address these points, in this paper, we introduce an additional input-free approach to perform portrait matting. We divide the task into two subtasks, segmentation and alpha matte prediction. We first generate a coarse segmentation map from the input image and then predict the alpha matte by utilizing the image and segmentation map. Besides, we present a segmentation encoding block to downsample the coarse segmentation map and provide useful feature representation to the residual block, since using a single encoder causes the vanishing of the segmentation information. We tested our model on four different benchmark datasets. The proposed method outperformed the MODNet and MGMatting methods that also take a single input. Besides, we obtained comparable results with BGM-V2 and FBA methods that require additional input.
UR - http://www.scopus.com/inward/record.url?scp=85137773331&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137773331&partnerID=8YFLogxK
U2 - 10.1109/CVPRW56347.2022.00085
DO - 10.1109/CVPRW56347.2022.00085
M3 - Conference contribution
AN - SCOPUS:85137773331
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 695
EP - 704
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
PB - IEEE Computer Society
T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Y2 - 19 June 2022 through 20 June 2022
ER -