paper-with-me

Papers

Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning

2022-10-14 · Donggeun Yoon, Jinsun Park, Donghyeon Cho

Recently, alpha matting has received a lot of attention because of its usefulness in mobile applications such as selfies. Therefore, there has been a demand for a lightweight alpha matting model due to the limited computational resources of commercial portable devices. To this end, we suggest a distillation-based channel pruning method for the alpha matting networks. In the pruning step, we remove channels of a student network having fewer impacts on mimicking the knowledge of a teacher network. Then, the pruned lightweight student network is trained by the same distillation loss. A lightweight alpha matting model from the proposed method outperforms existing lightweight methods. To show superiority of our algorithm, we provide various quantitative and qualitative experiments with in-depth analyses. Furthermore, we demonstrate the versatility of the proposed distillation-based channel pruning method by applying it to semantic segmentation.

📄 PDF Abstract BibTeX arXiv:2210.07760

Code (1)

donggeun-yoon/dcp 공식 구현 pytorch

Tasks

Image MattingSemantic Segmentation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Background Matting

2020-02-11 · Hossein Javidnia, François Pitié

The current state of the art alpha matting methods mainly rely on the trimap as the secondary and only guidance to estimate alpha. This paper investigates the effects of utilising the background information as well as tr…

Image MattingVideo Matting

Highly Efficient Natural Image Matting

2021-10-25 · Yijie Zhong, Bo Li, Lv Tang, Hao Tang 외

Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. However, there are still two drawbacks that impede the widespread application of image matting: the…

Image Matting

Attention-Guided Hierarchical Structure Aggregation for Image Matting

2020-06-01 · CVPR 2020 6 · Yu Qiao, Yuhao Liu, Xin Yang, Dongsheng Zhou 외

Existing deep learning based matting algorithms primarily resort to high-level semantic features to improve the overall structure of alpha mattes. However, we argue that advanced semantics extracted from CNNs contribute …

Image MattingSSIM

Hierarchical and Progressive Image Matting

2022-10-13 · Yu Qiao, Yuhao Liu, Ziqi Wei, Yuxin Wang 외

Most matting researches resort to advanced semantics to achieve high-quality alpha mattes, and direct low-level features combination is usually explored to complement alpha details. However, we argue that appearance-agno…

Image MattingSSIM

PolarMatte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting

2024-01-01 · CVPR 2024 1 · Kenji Enomoto, TJ Rhodes, Brian Price, Gavin Miller

The creation of high-quality alpha mattes as ground-truth data for video matting is typically a laborious task. The trade-off between accuracy manual corrections and capture constraints often produces erroneous resul…

Image MattingVideo Matting