Pre-Trained Image Processing Transformer
This work provides a generalizable pre-trained model for researchers and practitioners in low-level computer vision, offering improved performance across multiple tasks.
This paper introduces the Image Processing Transformer (IPT), a pre-trained model for low-level computer vision tasks like denoising and super-resolution. It leverages the ImageNet dataset to create corrupted image pairs for training and uses multi-heads, multi-tails, and contrastive learning. IPT achieves state-of-the-art performance on various benchmarks with a single pre-trained model.
As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly contributed to the representation ability of transformer and its variant architectures. In this paper, we study the low-level computer vision task (e.g., denoising, super-resolution and deraining) and develop a new pre-trained model, namely, image processing transformer (IPT). To maximally excavate the capability of transformer, we present to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs. The IPT model is trained on these images with multi-heads and multi-tails. In addition, the contrastive learning is introduced for well adapting to different image processing tasks. The pre-trained model can therefore efficiently employed on desired task after fine-tuning. With only one pre-trained model, IPT outperforms the current state-of-the-art methods on various low-level benchmarks. Code is available at https://github.com/huawei-noah/Pretrained-IPT and https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/IPT