paper-with-me

Papers

MatteFormer: Transformer-Based Image Matting via Prior-Tokens

2022-03-29 · CVPR 2022 1 · Gyutae Park, Sungjoon Son, Jaeyoung Yoo, SeHo Kim, Nojun Kwak

In this paper, we propose a transformer-based image matting model called MatteFormer, which takes full advantage of trimap information in the transformer block. Our method first introduces a prior-token which is a global representation of each trimap region (e.g. foreground, background and unknown). These prior-tokens are used as global priors and participate in the self-attention mechanism of each block. Each stage of the encoder is composed of PAST (Prior-Attentive Swin Transformer) block, which is based on the Swin Transformer block, but differs in a couple of aspects: 1) It has PA-WSA (Prior-Attentive Window Self-Attention) layer, performing self-attention not only with spatial-tokens but also with prior-tokens. 2) It has prior-memory which saves prior-tokens accumulatively from the previous blocks and transfers them to the next block. We evaluate our MatteFormer on the commonly used image matting datasets: Composition-1k and Distinctions-646. Experiment results show that our proposed method achieves state-of-the-art performance with a large margin. Our codes are available at https://github.com/webtoon/matteformer.

📄 PDF Abstract BibTeX arXiv:2203.15662

Code (1)

webtoon/matteformer 공식 구현 pytorch

Tasks

Image Matting

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Swin Transformer 설명 없음
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…

Similar Papers 제목 키워드 기반

TransMatting: Enhancing Transparent Objects Matting with Transformers

2022-08-05 · Huanqia Cai, Fanglei Xue, Lele Xu, Lili Guo

Image matting refers to predicting the alpha values of unknown foreground areas from natural images. Prior methods have focused on propagating alpha values from known to unknown regions. However, not all natural images h…

DecoderImage MattingTransparent objects

TransMatting: Tri-token Equipped Transformer Model for Image Matting

2023-03-11 · Huanqia Cai, Fanglei Xue, Lele Xu, Lili Guo

Image matting aims to predict alpha values of elaborate uncertainty areas of natural images, like hairs, smoke, and spider web. However, existing methods perform poorly when faced with highly transparent foreground objec…

Image MattingTransparent objects

ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers

2023-05-24 · Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered th…

Image Matting

Memory Efficient Matting with Adaptive Token Routing

2024-12-14 · Yiheng Lin, Yihan Hu, Chenyi Zhang, Ting Liu 외

Transformer-based models have recently achieved outstanding performance in image matting. However, their application to high-resolution images remains challenging due to the quadratic complexity of global self-attention.…

Image Matting

Towards Natural Image Matting in the Wild via Real-Scenario Prior

2024-10-09 · Ruihao Xia, Yu Liang, Peng-Tao Jiang, Hao Zhang 외

Recent approaches attempt to adapt powerful interactive segmentation models, such as SAM, to interactive matting and fine-tune the models based on synthetic matting datasets. However, models trained on synthetic data fai…

DecoderImage MattingInteractive SegmentationSemantic Segmentation