7d6354e047
* First draft * Simplify image processor * Fix rebase * Address comments * Address more comments * Address more comments * Address more comments * Address more comments * Improve pad_image * Add tests * Update integration test * Fix image processor tests * Fix model tests * Convert checkpoints * Fix doc tests * Remove file * Apply suggestions * Address comments * Fix typing hint * Add batch_norm_eps * Address comments * Fix style
2.7 KiB
VitMatte
Overview
The VitMatte model was proposed in Boosting Image Matting with Pretrained Plain Vision Transformers by Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang. VitMatte leverages plain Vision Transformers for the task of image matting, which is the process of accurately estimating the foreground object in images and videos.
The abstract from the paper is the following:
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 the problem of image matting. We hypothesize that image matting could also be boosted by ViTs and present a new efficient and robust ViT-based matting system, named ViTMatte. Our method utilizes (i) a hybrid attention mechanism combined with a convolution neck to help ViTs achieve an excellent performance-computation trade-off in matting tasks. (ii) Additionally, we introduce the detail capture module, which just consists of simple lightweight convolutions to complement the detailed information required by matting. To the best of our knowledge, ViTMatte is the first work to unleash the potential of ViT on image matting with concise adaptation. It inherits many superior properties from ViT to matting, including various pretraining strategies, concise architecture design, and flexible inference strategies. We evaluate ViTMatte on Composition-1k and Distinctions-646, the most commonly used benchmark for image matting, our method achieves state-of-the-art performance and outperforms prior matting works by a large margin.
Tips:
- The model expects both the image and trimap (concatenated) as input. One can use [
ViTMatteImageProcessor] for this purpose.
This model was contributed by nielsr. The original code can be found here.
VitMatteConfig
autodoc VitMatteConfig
VitMatteImageProcessor
autodoc VitMatteImageProcessor - preprocess
VitMatteForImageMatting
autodoc VitMatteForImageMatting - forward