MZNet reports state-of-the-art moiré removal on high-resolution benchmarks with a U-Net combining multi-scale dual attention, multi-shape large-kernel convolutions, and fused skip connections.
Pre-Trained Image Processing Transformer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Moir\'e Zero: An Efficient and High-Performance Neural Architecture for Moir\'e Removal
MZNet reports state-of-the-art moiré removal on high-resolution benchmarks with a U-Net combining multi-scale dual attention, multi-shape large-kernel convolutions, and fused skip connections.