Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 266

The DOI matches its Crossref record; 97 of the 97 references it cites were found in a registry or an index.

MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration

Open access
Jin, Zhi, Qiu, Yuwei, Zhang, Kaihao, Li, Hongdong, Luo, Wenhan·2025·IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

Recently, Transformer networks have demonstrated outstanding performance in the field of image restoration due to the global receptive field and adaptability to input. However, the quadratic computational complexity of Softmax-attention poses a significant limitation on its extensive application in image restoration tasks, particularly for high-resolution images. To tackle this challenge, we propose a novel variant of the Transformer. This variant leverages the Taylor expansion to approximate the Softmax-attention and utilizes the concept of norm-preserving mapping to approximate the remainder of the first-order Taylor expansion, resulting in a linear computational complexity. Moreover, we introduce a multi-branch architecture featuring multi-scale patch embedding into the proposed Transformer, which has four distinct advantages: 1) various sizes of the receptive field; 2) multi-level semantic information; 3) flexible shapes of the receptive field; 4) accelerated training and inference speed. Hence, the proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2) has the capability to concurrently process coarse-to-fine features, capture long-distance pixel interactions with limited computational cost, and improve the approximation of the Taylor expansion remainder. Experimental results across diverse image restoration benchmarks demonstrate that MB-TaylorFormer V2 achieves state-of-the-art performance in multiple image restoration tasks, such as image dehazing, deraining, desnowing, motion deblurring, and denoising, with very little computational overhead.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2025.3559891

Cites

97 of 97 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 97 references

Research works printed but not linked: 6

  1. Qin, cosFormer: Rethinking softmax in attention, 1
  2. Si, Inception transformer, 23495
  3. Simonyan, Very deep convolutional networks for large-scale image recognition, 1
  4. 10.48550/ARXIV.1706.03762 · DOI · Paper page
  5. Cui, IRNeXt: Rethinking convolutional network design for image restoration, 6545
  6. Yue, Variational denoising network: Toward blind noise modeling and removal, 1690

Metadata

Authors
Jin, Z., Qiu, Y., Zhang, K., Li, H., & Luo, W.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2025-07
Volume
47
Issue
7
Pages
5990-6005
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W4409326045
Cited by
266
References
97
FWCI
97.33
Type
journal article
Language
en
Open access
green
Funders
  • National Natural Science Foundation of China (U24A20251, 62372480)
  • Shenzhen Science and Technology Program (JCYJ20230807111107015, JCYJ20240813110459017)
  • Fundamental Research Funds for the Central Universities
  • Sun Yat-sen University (24lgqb015)
  • Basic and Applied Basic Research Foundation of Guangdong Province (2025A1515011361)
  • Science Fund Program for Young Scientists Fund (62406089)
  • ARC-Discovery (DP 220100800)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration. https://app.cochat.ai/papers/10.1109/tpami.2025.3559891
The paper
Jin, Z., Qiu, Y., Zhang, K., Li, H., & Luo, W. (2025). MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2025.3559891

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.