Training Matting Models without Alpha Labels

• URL: http://arxiv.org/abs/2408.10539v1
• Date: Tue, 20 Aug 2024 04:34:06 GMT
• Title: Training Matting Models without Alpha Labels
• Authors: Wenze Liu, Zixuan Ye, Hao Lu, Zhiguo Cao, Xiangyu Yue,
• Abstract summary: This work explores using rough annotations such as trimaps coarsely indicating the foreground/background as supervision. We present that the cooperation between learned semantics from indicated known regions and proper assumed matting rules can help infer alpha values at transition areas. Experiments on AM-2K and P3M-10K dataset show that our paradigm achieves comparable performance with the fine-label-supervised baseline.
• Score: 22.249204770416927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The labelling difficulty has been a longstanding problem in deep image matting. To escape from fine labels, this work explores using rough annotations such as trimaps coarsely indicating the foreground/background as supervision. We present that the cooperation between learned semantics from indicated known regions and proper assumed matting rules can help infer alpha values at transition areas. Inspired by the nonlocal principle in traditional image matting, we build a directional distance consistency loss (DDC loss) at each pixel neighborhood to constrain the alpha values conditioned on the input image. DDC loss forces the distance of similar pairs on the alpha matte and on its corresponding image to be consistent. In this way, the alpha values can be propagated from learned known regions to unknown transition areas. With only images and trimaps, a matting model can be trained under the supervision of a known loss and the proposed DDC loss. Experiments on AM-2K and P3M-10K dataset show that our paradigm achieves comparable performance with the fine-label-supervised baseline, while sometimes offers even more satisfying results than human-labelled ground truth. Code is available at \url{https://github.com/poppuppy/alpha-free-matting}.

Related papers

• Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models [55.99654128127689]
  Visual Foundation Models (VFMs) are used to enhance 3D representation learning. VFMs generate semantic labels for weakly-supervised pixel-to-point contrastive distillation. We adapt sampling probabilities of points to address imbalances in spatial distribution and category frequency.
  arXiv  Detail & Related papers  (2024-05-23T07:48:19Z)
• 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)
• Self-supervised Matting-specific Portrait Enhancement and Generation [40.444011984347505]
  We use StyleGAN to explore the latent space of GAN models. We optimize multi-scale latent vectors in the latent spaces under four tailored losses. We show that the proposed method can refine real portrait images for arbitrary matting models.
  arXiv  Detail & Related papers  (2022-08-13T09:00:02Z)
• Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation [49.59567529191423]
  We propose a novel semi-supervised learning framework for segmentation of volumetric images from new unlabeled domains. We jointly use supervised and contrastive learning, also introducing a contrastive pairing scheme that leverages similarity between nearby slices in 3D.
  arXiv  Detail & Related papers  (2022-03-07T19:02:26Z)
• Long-Range Feature Propagating for Natural Image Matting [93.20589403997505]
  Natural image matting estimates alpha values of unknown regions in the trimap. Recently, deep learning based methods propagate the alpha values from the known regions to unknown regions according to the similarity between them. We propose Long-Range Feature Propagating Network (LFPNet), which learns the long-range context features outside the reception fields for alpha matte estimation.
  arXiv  Detail & Related papers  (2021-09-25T01:17:17Z)
• Alpha Matte Generation from Single Input for Portrait Matting [79.62140902232628]
  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. We introduce an additional input-free approach to perform portrait matting using Generative Adversarial Nets (GANs)
  arXiv  Detail & Related papers  (2021-06-06T18:53:42Z)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)

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.