Deep Image Matting

Xu, Ning; Price, Brian; Cohen, Scott; Huang, Tsung‐Wei

doi:10.1109/cvpr.2017.41

Cited by 471 publications

(814 citation statements)

References 31 publications

(97 reference statements)

Supporting

Mentioning

757

Contrasting

Order By: Relevance

“…We experiment with our methods on the synthetic Composition-1K dataset and a real-world matting image dataset, both of which are provided by Xu et al [52]. As discussed in Section 3.2, our neural networks are all trained on the synthetic Composition-1K training set.…”

Section: Methodsmentioning

confidence: 99%

“…They were generated by compositing 50 unique foreground images onto each of the 20 images from the PASCAL VOC 2012 dataset [15]. We used the code provided by Xu et al [52] to generate these testing images. The real world image dataset contains 31 real world images pulled from the internet [52].…”

Section: Methodsmentioning

confidence: 99%

“…We used the code provided by Xu et al [52] to generate these testing images. The real world image dataset contains 31 real world images pulled from the internet [52]. We conduct our user study on the real world images.…”

Section: Methodsmentioning

confidence: 99%

“…As illustrated in Figure 5, our method is stable to the trimap sizes. Note, the scores of comparing methods were obtained from [52].…”

Section: Evaluation On Alpha Mapsmentioning

confidence: 99%

See 3 more Smart Citations

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Hou

Liu

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

158

166

View full text Add to dashboard Cite

Natural image matting is an important problem in computer vision and graphics. It is an ill-posed problem when only an input image is available without any external information. While the recent deep learning approaches have shown promising results, they only estimate the alpha matte. This paper presents a context-aware natural image matting method for simultaneous foreground and alpha matte estimation. Our method employs two encoder networks to extract essential information for matting. Particularly, we use a matting encoder to learn local features and a context encoder to obtain more global context information. We concatenate the outputs from these two encoders and feed them into decoder networks to simultaneously estimate the foreground and alpha matte. To train this whole deep neural network, we employ both the standard Laplacian loss and the feature loss: the former helps to achieve high numerical performance while the latter leads to more perceptually plausible results. We also report several data augmentation strategies that greatly improve the network's generalization performance. Our qualitative and quantitative experiments show that our method enables high-quality matting for a single natural image. Our inference codes and models have been made publicly available at https://github. com/hqqxyy/Context-Aware-Matting.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…As illustrated in Figure 5, our method is stable to the trimap sizes. Note, the scores of comparing methods were obtained from [52].…”

Section: Evaluation On Alpha Mapsmentioning

confidence: 99%

See 2 more Smart Citations

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Hou

Liu

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

158

166

View full text Add to dashboard Cite

show abstract

“…In these cases the cost of pixel-level annotation can be reduced by automating a portion of the task. Matting and object selection [50,33,34,6,58,57,10,30,59] generate tight boundaries from loosely annotated boundaries or few inside/outside clicks and scribbles. [44,38] introduced a predictive method which automatically infers a foreground mask from 4 boundary clicks, and was extended to full-image segmentation in [2].…”

Section: Related Workmentioning

confidence: 99%

Block Annotation: Better Image Annotation With Sub-Image Decomposition

Lin

Upchurch

Bala

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Image datasets with high-quality pixel-level annotations are valuable for semantic segmentation: labelling every pixel in an image ensures that rare classes and small objects are annotated. However, full-image annotations are expensive, with experts spending up to 90 minutes per image. We propose block sub-image annotation as a replacement for full-image annotation. Despite the attention cost of frequent task switching, we find that block annotations can be crowdsourced at higher quality compared to full-image annotation with equal monetary cost using existing annotation tools developed for full-image annotation. Surprisingly, we find that 50% pixels annotated with blocks allows semantic segmentation to achieve equivalent performance to 100% pixels annotated. Furthermore, as little as 12% of pixels annotated allows performance as high as 98% of the performance with dense annotation. In weakly-supervised settings, block annotation outperforms existing methods by 3-4% (absolute) given equivalent annotation time. To recover the necessary global structure for applications such as characterizing spatial context and affordance relationships, we propose an effective method to inpaint block-annotated images with high-quality labels without additional human effort. As such, fewer annotations can also be used for these applications compared to full-image annotation.

show abstract

Automating Hair Loss Labels for Universally Scoring Alopecia From Images

et al. 2023

View full text Add to dashboard Cite

ImportanceClinical estimation of hair density has an important role in assessing and tracking the severity and progression of alopecia, yet to the authors’ knowledge, no automation currently exists for this process. While some algorithms have been developed to assess alopecia presence on a binary level, their scope has been limited by focusing on a re-creation of the Severity of Alopecia Tool (SALT) score for alopecia areata (AA). Yet hair density loss is common to all alopecia forms, and an evaluation of that loss is used in established scoring systems for androgenetic alopecia (AGA), central centrifugal cicatricial alopecia (CCCA), and many more.ObjectiveTo develop and validate a new model, HairComb, to automatically compute the percentage hair loss from images regardless of alopecia subtype.Design, Setting, and ParticipantsIn this research study to create a new algorithmic quantification system for all hair loss, computational imaging analysis and algorithm design using retrospective image data collection were performed. This was a multicenter study, where images were collected at the Children’s Hospital of Philadelphia, University of Pennsylvania (Penn), and via a Penn Dermatology web interface. Images were collected from 2015 to 2021, and they were analyzed from 2019 to 2021.Main Outcomes and MeasuresScoring systems correlation analysis was measured by linear and logarithmic regressions. Algorithm performance was evaluated using image segmentation accuracy, density probability regression error, and average percentage hair loss error for labeled images, and Pearson correlation for manual scores.ResultsThere were 404 participants aged 2 years and older that were used for designing and validating HairComb. Scoring systems correlation analysis was performed for 250 participants (70.4% female; mean age, 35.3 years): 75 AGA, 66 AA, 50 CCCA, 27 other alopecia diagnoses (frontal fibrosing alopecia, lichen planopilaris, telogen effluvium, etc), and 32 unaffected scalps without alopecia. Scoring systems showed strong correlations with underlying percentage hair loss, with coefficient of determination R2 values of 0.793 and 0.804 with respect to log of percentage hair loss. Using HairComb, 92% accuracy, 5% regression error, 7% hair loss difference, and predicted scores with errors comparable to annotators were achieved.Conclusions and RelevanceIn this research study,it is shown that an algorithm quantitating percentage hair loss may be applied to all forms of alopecia. A generalizable automated assessment of hair loss would provide a way to standardize measurements of hair loss across a range of conditions.

show abstract

Deep Image Matting

Cited by 471 publications

References 31 publications

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Block Annotation: Better Image Annotation With Sub-Image Decomposition

Automating Hair Loss Labels for Universally Scoring Alopecia From Images

Contact Info

Product

Resources

About