High-Resolution Deep Image Matting

• URL: http://arxiv.org/abs/2009.06613v2
• Date: Fri, 15 Jan 2021 08:14:55 GMT
• Title: High-Resolution Deep Image Matting
• Authors: Haichao Yu, Ning Xu, Zilong Huang, Yuqian Zhou, Humphrey Shi
• Abstract summary: HDMatt is a first deep learning based image matting approach for high-resolution inputs. Our proposed method sets new state-of-the-art performance on Adobe Image Matting and AlphaMatting benchmarks.
• Score: 39.72708676319803
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image matting is a key technique for image and video editing and composition. Conventionally, deep learning approaches take the whole input image and an associated trimap to infer the alpha matte using convolutional neural networks. Such approaches set state-of-the-arts in image matting; however, they may fail in real-world matting applications due to hardware limitations, since real-world input images for matting are mostly of very high resolution. In this paper, we propose HDMatt, a first deep learning based image matting approach for high-resolution inputs. More concretely, HDMatt runs matting in a patch-based crop-and-stitch manner for high-resolution inputs with a novel module design to address the contextual dependency and consistency issues between different patches. Compared with vanilla patch-based inference which computes each patch independently, we explicitly model the cross-patch contextual dependency with a newly-proposed Cross-Patch Contextual module (CPC) guided by the given trimap. Extensive experiments demonstrate the effectiveness of the proposed method and its necessity for high-resolution inputs. Our HDMatt approach also sets new state-of-the-art performance on Adobe Image Matting and AlphaMatting benchmarks and produce impressive visual results on more real-world high-resolution images.

Related papers

• DiffusionMat: Alpha Matting as Sequential Refinement Learning [87.76572845943929]
  DiffusionMat is an image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. A correction module adjusts the output at each denoising step, ensuring that the final result is consistent with the input image's structures. We evaluate our model across several image matting benchmarks, and the results indicate that DiffusionMat consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2023-11-22T17:16:44Z)
• DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches [8.812837829361923]
  We propose the Dynamic Backward Attention Transformer (DBAT) to aggregate cross-resolution features. Experiments show that our DBAT achieves an accuracy of 86.85%, which is the best performance among state-of-the-art real-time models. We further align features to semantic labels, performing network dissection, to infer that the proposed model can extract material-related features better than other methods.
  arXiv  Detail & Related papers  (2023-05-06T03:47:20Z)
• Deep Image Matting: A Comprehensive Survey [85.77905619102802]
  This paper presents a review of recent advancements in image matting in the era of deep learning. We focus on two fundamental sub-tasks: auxiliary input-based image matting and automatic image matting. We discuss relevant applications of image matting and highlight existing challenges and potential opportunities for future research.
  arXiv  Detail & Related papers  (2023-04-10T15:48:55Z)
• Smart Scribbles for Image Mating [90.18035889903909]
  We propose an interactive framework, referred to as smart scribbles, to guide users to draw few scribbles on the input images. It infers the most informative regions of an image for drawing scribbles to indicate different categories. It then spreads these scribbles to the rest of the image via our well-designed two-phase propagation.
  arXiv  Detail & Related papers  (2021-03-31T13:30:49Z)
• Semantic Layout Manipulation with High-Resolution Sparse Attention [106.59650698907953]
  We tackle the problem of semantic image layout manipulation, which aims to manipulate an input image by editing its semantic label map. A core problem of this task is how to transfer visual details from the input images to the new semantic layout while making the resulting image visually realistic. We propose a high-resolution sparse attention module that effectively transfers visual details to new layouts at a resolution up to 512x512.
  arXiv  Detail & Related papers  (2020-12-14T06:50:43Z)
• Bridging Composite and Real: Towards End-to-end Deep Image Matting [88.79857806542006]
  We study the roles of semantics and details for image matting. We propose a novel Glance and Focus Matting network (GFM), which employs a shared encoder and two separate decoders. Comprehensive empirical studies have demonstrated that GFM outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-30T10:57:13Z)
• Hierarchical Opacity Propagation for Image Matting [15.265494938937737]
  A novel structure for more direct alpha matte propagation between pixels is in demand. HOP matting is capable of outperforming state-of-the-art matting methods.
  arXiv  Detail & Related papers  (2020-04-07T10:39:55Z)
• Natural Image Matting via Guided Contextual Attention [18.034160025888056]
  We develop a novel end-to-end approach for natural image matting with a guided contextual attention module. The proposed method can mimic information flow of affinity-based methods and utilize rich features learned by deep neural networks simultaneously. Experiment results on Composition-1k testing set and alphamatting.com benchmark dataset demonstrate that our method outperforms state-of-the-art approaches in natural image matting.
  arXiv  Detail & Related papers  (2020-01-13T05:59:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.