Towards Light‐Weight Portrait Matting via Parameter Sharing

Dai, Yutong; Lu, Hao; Shen, Chunhua

doi:10.1111/cgf.14179

Cited by 6 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Decoder Design. Various decoder designs [1,4,5,18,22,37] have been studied in matting models. As the bridge to recover resolutions and capture details, the decoder matters for matting.…”

Section: A Strong Matting Framework With Context Assemblingmentioning

confidence: 99%

Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation

Dai¹,

Price²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

SIM GCA IndexNet FBA CA+DA Ours Figure 1. Matting results on real-world images. From the second column to right are results of IndexNet [22], GCA [18], SIM [28], FBA [11], CA+data augmentation (DA) [14] and our method, respectively. Note that, all the methods are trained with the DIM [34]dataset (except SIM is trained with the SIMD [28] dataset). They are comparable on benchmark images, while presents varying results on real-world images. Our method shows better generalization ability.

show abstract

“…Decoder Design. Various decoder designs [1,4,5,18,22,37] have been studied in matting models. As the bridge to recover resolutions and capture details, the decoder matters for matting.…”

Section: A Strong Matting Framework With Context Assemblingmentioning

confidence: 99%

Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation

Dai¹,

Price²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent deep learning methods have achieved encouraging results on natural image matting [LDSX19, LL20, STT21], portrait matting [STG*16, DLS21], and human matting [CGX*18, LYH*20, LRS*21, SJC*20, YZZ*21]. Prior‐based methods [XPCH17, AOAP17, YZZ*21, LXZ*21] take an image and a prior (mask, trimap, etc.)…”

Section: Related Workmentioning

confidence: 99%

Effective Eyebrow Matting with Domain Adaptation

Wang

Zhang

Xiao

et al. 2022

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

O r i g i n a l ( g ) P a r a me t e r i z a o n o f ( f ) ( h ) E y e b r o w r e mo v a l ( i ) P a r a me t e r i z a o n o f ( h ) Figure 1: We create the first synthetic eyebrow matting dataset (a). This enables semi-supervised training of a domain adaptation eyebrow matting network. The network can learn domain-robust features from synthetic data (a) together with unlabeled real-world eyebrow images without using any real matting data and estimate high-quality eyebrow alpha matte (c) from a real RGB image (b) only without any prior.The eyebrow matting allows us to automatically remove the interference of eyebrows during the multi-view stereo (MVS) based 3D face reconstruction process, and therefore largely enhances the efficiency and efficacy of the reconstruction of eyebrow regions. Without eyebrow removal, the reconstructed eyebrow geometry (f) often induces noises and artifacts when fitting the eyebrow during 3D parametric face reconstruction (g), which requires very expensive manual repair in hours. In contrast, eyebrow matting facilitates the easy attainment of better geometry (h) and more faithful parameterization of the eyebrow region (i). Furthermore, our eyebrow matting method can be used for cosmetic design purposes such as eyebrow recoloring (d) and eyebrow replacement (e).

show abstract

“…Besides, to perform generalization for other domains, another matting network is trained in relating with the first network. In [9], the authors proposed a light-weight portrait matting method. Two decoders and a single encoder are employed in the system.…”

Section: Image Mattingmentioning

confidence: 99%

Alpha Matte Generation from Single Input for Portrait Matting

Yaman¹,

Ekenel²,

Waibel³

2021

Preprint

View full text Add to dashboard Cite

Portrait matting is an important research problem with a wide range of applications, such as video conference app, image/video editing, and post-production. 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, providing additional input is not always practical. Besides, models are too sensitive to these additional inputs. In this paper, we introduce an additional input-free approach to perform portrait matting using Generative Adversarial Nets (GANs). We divide the main task into two subtasks. For this, we propose a segmentation network for the person segmentation and the alpha generation network for alpha matte prediction. While the segmentation network takes an input image and produces a coarse segmentation map, the alpha generation network utilizes the same input image as well as a coarse segmentation map that is produced by the segmentation network to predict the alpha matte. Besides, we present a segmentation encoding block to downsample the coarse segmentation map and provide feature representation to the residual block. Furthermore, we propose border loss to penalize only the borders of the subject separately which is more likely to be challenging and we also adapt perceptual loss for portrait matting. To train the proposed system, we combine two different popular training datasets to improve the amount of data as well as diversity to address domain shift problems in the inference time. We tested our model on three different benchmark datasets, namely Adobe Image Matting dataset, Portrait Matting dataset, and Distinctions dataset. The proposed method outperformed the MODNet method that also takes a single input. Besides, we obtained comparable results with BGM-V2 and FBA methods that require additional input.

show abstract

Towards Light‐Weight Portrait Matting via Parameter Sharing

Cited by 6 publications

References 33 publications

Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation

Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation

Effective Eyebrow Matting with Domain Adaptation

Alpha Matte Generation from Single Input for Portrait Matting

Contact Info

Product

Resources

About