Learning Affinity-Aware Upsampling for Deep Image Matting

• URL: http://arxiv.org/abs/2011.14288v1
• Date: Sun, 29 Nov 2020 05:09:43 GMT
• Title: Learning Affinity-Aware Upsampling for Deep Image Matting
• Authors: Yutong Dai, Hao Lu, Chunhua Shen
• Abstract summary: We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. In particular, results on the Composition-1k matting dataset show that A2U achieves a 14% relative improvement in the SAD metric against a strong baseline. Compared with the state-of-the-art matting network, we achieve 8% higher performance with only 40% model complexity.
• Score: 83.02806488958399
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. Second-order features are commonly used in dense prediction to build adjacent relations with a learnable module after upsampling such as non-local blocks. Since upsampling is essential, learning affinity in upsampling can avoid additional propagation layers, offering the potential for building compact models. By looking at existing upsampling operators from a unified mathematical perspective, we generalize them into a second-order form and introduce Affinity-Aware Upsampling (A2U) where upsampling kernels are generated using a light-weight lowrank bilinear model and are conditioned on second-order features. Our upsampling operator can also be extended to downsampling. We discuss alternative implementations of A2U and verify their effectiveness on two detail-sensitive tasks: image reconstruction on a toy dataset; and a largescale image matting task where affinity-based ideas constitute mainstream matting approaches. In particular, results on the Composition-1k matting dataset show that A2U achieves a 14% relative improvement in the SAD metric against a strong baseline with negligible increase of parameters (<0.5%). Compared with the state-of-the-art matting network, we achieve 8% higher performance with only 40% model complexity.

Related papers

• Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels [18.729177307412645]
  We propose a lightweight upsampling operation, termed Dynamic Lightweight Upsampling (DLU) Experiments on several mainstream vision tasks show that our DLU achieves comparable and even better performance to the original CARAFE.
  arXiv  Detail & Related papers  (2024-10-29T15:35:14Z)
• Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling [2.1465347972460367]
  Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to interpret images accurately and predict detailed labels, resulting in diminished performance compared to processing at original resolutions. We introduce a novel method named Edge-preserving Probabilistic Downsampling (EPD) It utilizes class uncertainty within a local window to produce soft labels, with the window size dictating the downsampling factor.
  arXiv  Detail & Related papers  (2024-04-05T10:01:31Z)
• Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions [77.32043242988738]
  We propose a new framework for accurate point cloud upsampling that supports arbitrary upsampling rates. Our method first interpolates the low-res point cloud according to a given upsampling rate.
  arXiv  Detail & Related papers  (2023-04-24T06:36:35Z)
• BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling [60.257912103351394]
  We develop a new point cloud upsampling pipeline called BIMS-PU. We decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors. We show that our method achieves superior results to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-25T13:13:37Z)
• PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsampling [4.418205951027186]
  Upsampling sparse, noisy and nonuniform point clouds is a challenging task. A novel design of Edge Vector based Approximation for Flexible-scale Point clouds Upsampling (PU-EVA) is proposed. The EVA upsampling decouples the upsampling scales with network architecture, achieving the flexible upsampling rates in one-time training.
  arXiv  Detail & Related papers  (2022-04-22T15:14:05Z)
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation [79.60988242843437]
  We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-18T07:18:25Z)
• SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [52.20602782690776]
  It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data. We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2020-12-08T14:14:09Z)
• Adaptive Context-Aware Multi-Modal Network for Depth Completion [107.15344488719322]
  We propose to adopt the graph propagation to capture the observed spatial contexts. We then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2020-08-25T06:00:06Z)

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.