Papers › Pre-Trained Image Processing Transformer

Pre-Trained Image Processing Transformer

1 Dec 2020CVPR 2021 1arXiv:2012.00364archive 2025-07-28

Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, Wen Gao

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

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

huawei-noah/Pretrained-IPT officialmentioned in papermentioned on GitHubpytorch report
dongyan007/Pretrained-IPT-main-master mentioned on GitHubpytorch report
yangyucheng000/IPT-3 mentioned on GitHubmindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Color Image DenoisingContrastive LearningDenoisingImage Super-ResolutionRain RemovalSingle Image DerainingSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising CBSD68 sigma50 IPT PSNR 29.39 #1 of 18 Archive leaderboard report
Color Image Denoising Urban100 sigma50 IPT PSNR 29.71 #8 of 9 Archive leaderboard report
Image Super-Resolution BSD100 - 2x upscaling IPT PSNR 32.48 #13 of 30 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling IPT PSNR 30.85 #9 of 24 Archive leaderboard report
Image Super-Resolution Urban100 - 3x upscaling IPT PSNR 29.49 #9 of 22 Archive leaderboard report
Single Image Deraining Rain100L IPT PSNR 41.62 #1 of 19 Archive leaderboard report
Single Image Deraining Rain100L IPT SSIM 0.988 #1 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTContrastive LearningDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections