pith. sign in

arxiv: 2605.22186 · v1 · pith:GKKXWIV2new · submitted 2026-05-21 · 💻 cs.CV

Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Dataset

Senyan Xu , Zhijing Sun , Kean Liu , Xin Lu , Ruixuan Jiang , Mingyang Huang , Xueyang Fu , Zheng-Jun Zha This is my paper

Pith reviewed 2026-05-22 06:28 UTC · model grok-4.3

classification 💻 cs.CV
keywords low-light image enhancementevent cameraevent-based visionhybrid imagingreal-world datasetdynamic scenesimage denoising
0
0 comments X

The pith

Event and image illumination collaborate to enhance low-light photos with a new synchronized real-world dataset.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that low-light image enhancement improves when event camera signals, which supply high dynamic range details, interact directly with global illumination cues extracted from ordinary images. It introduces an interaction module that gathers features across lighting variations and injects complementary content back into both representations, plus a filter that uses image brightness statistics to suppress event noise. To enable this, the authors built a beam-splitter hybrid camera rig that records temporally aligned high-resolution event-image pairs from moving scenes. Experiments on five datasets show consistent gains over prior techniques. A reader would care because many practical vision tasks, from night photography to surveillance, still struggle with noisy or detail-poor results under poor lighting.

Core claim

The authors claim that an Event-Illumination Collaborative Interaction module, which gathers high-dynamic-range features forward across lighting conditions and injects complementary content backward, together with an Illumination-aware Event Filter that reduces event noise using brightness statistics from the image, produces better low-light enhancement than prior approaches. This is backed by the first high-resolution real-world event-based low-light dataset collected with a beam-splitter hybrid imaging system that ensures temporal synchronization in dynamic scenes.

What carries the argument

The Event-Illumination Collaborative Interaction (EICI) module that performs forward gathering of HDR features and backward injection of content, combined with the Illumination-aware Event Filter (IAEF) that dynamically reduces event noise according to image brightness statistics.

If this is right

  • The method outperforms prior state-of-the-art approaches on five real-world and synthetic datasets.
  • Quantitative gains reach up to 1.24 dB in PSNR and 0.069 in SSIM.
  • Event noise is reduced in real-world conditions by using image-derived brightness statistics.
  • The released high-resolution paired dataset supports future training and benchmarking of event-based enhancement techniques.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar collaboration between event and frame data could improve other low-light tasks such as object detection or tracking.
  • Widespread adoption of synchronized hybrid cameras might reduce reliance on separate high-dynamic-range sensors in consumer devices.
  • The filtering idea could be tested on video sequences to enforce temporal consistency across frames.

Load-bearing premise

The beam-splitter hybrid imaging system produces temporally synchronized, high-quality event-image pairs that represent real-world low-light dynamic scenes without introducing new artifacts or biases.

What would settle it

Measure whether the reported PSNR and SSIM gains disappear when the same method is tested on event-image pairs recorded by independent unsynchronized cameras or on scenes with known synchronization offsets.

Figures

Figures reproduced from arXiv: 2605.22186 by Kean Liu, Mingyang Huang, Ruixuan Jiang, Senyan Xu, Xin Lu, Xueyang Fu, Zheng-Jun Zha, Zhijing Sun.

Figure 1
Figure 1. Figure 1: Visual comparison of LIE methods on the proposed real [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: An overview of (a) our EIC-LIE. The core modules of EIC-LIE are (b) Event-Illumination Collaborative Interaction (EICI) and [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: (a) t-SNE analysis of features in EICI without attention reuse. Note that [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: The hardware implementation of our imaging system. In (d), from left to right, each represents low-light images, normal-light [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visual results on RLE dataset. Note that the crop of input has been gamma corrected, and other figures also follow this adjustment. [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Visual results on SDE [30]-indoor (left) and -outdoor (right). Zoom in for a better view. (a) Input (b) MambaLLIE (e) EvLight (f) Ours (g) GT (a) Input (b) MambaLLIE (e) EvLight (f) Ours (g) GT [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Visual results on SDSD [61]-indoor (left) and -outdoor (right). Zoom in for a better view. Case Guidance PSNR SSIM 0 - 19.53 0.6623 1 w. E 21.40 0.7287 2 w. I 21.08 0.7194 Ours w. I&E 23.63 0.7670 [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
read the original abstract

Event-based low-light image enhancement (LIE) methods mainly focus on incorporating high dynamic range (HDR) information from events while overlooking the essential global illumination in images and the inherent noise sensitivity of event signals in real-world scenarios. To address these issues, we propose EIC-LIE, an event-illumination collaborative LIE framework. Concretely, we first design an Event-Illumination Collaborative Interaction (EICI) module, which contains two key processes: forward gathering, which gathers HDR features across varying lighting conditions, and backward injection, which provides complementary content for illumination and event representations. Next, we introduce an Illumination-aware Event Filter (IAEF) that dynamically reduces event noise based on brightness statistics derived from images. Additionally, we build a beam-splitter-based hybrid imaging system to collect high-quality event-image pairs with temporal synchronization from dynamic scenes, providing the first high-resolution, real-world event-based LIE dataset. Extensive experiments show that our EIC-LIE outperforms state-of-the-art methods on five real-world and synthetic datasets, significantly surpassing previous methods with improvements of up to 1.24dB in PSNR and 0.069 in SSIM. The code and dataset are released at https://github.com/QUEAHREN/EIC-LIE.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper proposes EIC-LIE, an event-illumination collaborative framework for low-light image enhancement. It introduces an Event-Illumination Collaborative Interaction (EICI) module with forward gathering of HDR features and backward injection of complementary content, plus an Illumination-aware Event Filter (IAEF) to reduce event noise using image brightness statistics. A beam-splitter hybrid imaging system is used to capture a new high-resolution real-world event-image dataset with temporal synchronization. Experiments claim that EIC-LIE outperforms prior methods on five real-world and synthetic datasets, with gains up to 1.24 dB PSNR and 0.069 SSIM; code and dataset are released.

Significance. If the performance claims and dataset validity hold, the work would provide a practical advance in event-based low-light enhancement by jointly addressing illumination and event noise, while the released high-resolution real-world dataset and code would be a concrete contribution for future benchmarking. The modular design (EICI + IAEF) offers a clear architectural template that could be adapted beyond the specific task.

major comments (1)
  1. [§4] §4 (Dataset Collection and Validation): The central real-world performance gains (up to 1.24 dB PSNR) rest on the unverified assumption that the beam-splitter hybrid system produces temporally synchronized, artifact-free event-image pairs representative of natural low-light dynamics. No quantitative validation—such as spatial/temporal alignment error histograms, cross-capture PSNR between split paths, or noise-statistic comparisons—is reported; without this, the reported margins on the new dataset risk being method-specific rather than generalizable.
minor comments (2)
  1. [Abstract, §5] Abstract and §5: The phrase 'significantly surpassing previous methods' is used without accompanying statistical significance tests or error bars on the reported PSNR/SSIM deltas; adding these would strengthen the quantitative claims.
  2. [§3.2] §3.2 (IAEF): The dynamic noise reduction is described as depending on 'brightness statistics derived from images,' but the exact formulation (e.g., whether it is a learned attention map or a fixed threshold) is not stated in sufficient detail for reproduction.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive and detailed review. The feedback on dataset validation is particularly helpful, and we address it directly below. We will revise the manuscript accordingly to strengthen the presentation of our contributions.

read point-by-point responses

  1. Referee: [§4] §4 (Dataset Collection and Validation): The central real-world performance gains (up to 1.24 dB PSNR) rest on the unverified assumption that the beam-splitter hybrid system produces temporally synchronized, artifact-free event-image pairs representative of natural low-light dynamics. No quantitative validation—such as spatial/temporal alignment error histograms, cross-capture PSNR between split paths, or noise-statistic comparisons—is reported; without this, the reported margins on the new dataset risk being method-specific rather than generalizable.

    Authors: We agree that explicit quantitative validation of the acquisition system would better support the claims regarding temporal synchronization and data quality. In the revised manuscript we will add a dedicated validation subsection (or appendix) that reports spatial and temporal alignment error histograms, cross-capture PSNR between the two split paths, and noise-statistic comparisons. These metrics will be computed directly from the captured pairs and will demonstrate that the beam-splitter system yields artifact-free, temporally synchronized event-image data representative of natural low-light scenes, thereby confirming that the reported performance margins are not method-specific. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected in derivation or claims.

full rationale

The paper introduces a new EIC-LIE architecture with explicitly defined EICI module (forward gathering and backward injection) and IAEF filter, plus a beam-splitter capture system for a novel high-resolution dataset. Performance claims rest on standard PSNR/SSIM evaluation across five datasets using conventional metrics, without any equations or steps that reduce predictions to fitted parameters by construction, self-definitional loops, or load-bearing self-citations. The central contributions are architectural and empirical, remaining independent of the reported results.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on the effectiveness of the proposed EICI module and IAEF filter plus the representativeness of the new beam-splitter dataset. No explicit free parameters, axioms, or invented entities are named in the abstract; the network presumably contains standard deep-learning hyperparameters that are not detailed here.

pith-pipeline@v0.9.0 · 5783 in / 1199 out tokens · 26667 ms · 2026-05-22T06:28:04.149224+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

82 extracted references · 82 canonical work pages · 2 internal anchors

  1. [1]

    Xcit: Cross-covariance image transformers.Advances in neural information processing systems, 34:20014–20027, 2021

    Alaaeldin Ali, Hugo Touvron, Mathilde Caron, Piotr Bo- janowski, Matthijs Douze, Armand Joulin, Ivan Laptev, Na- talia Neverova, Gabriel Synnaeve, Jakob Verbeek, et al. Xcit: Cross-covariance image transformers.Advances in neural information processing systems, 34:20014–20027, 2021. 4

    work page 2021

  2. [2]

    A his- togram modification framework and its application for image contrast enhancement.IEEE Transactions on image process- ing, 18(9):1921–1935, 2009

    Tarik Arici, Salih Dikbas, and Yucel Altunbasak. A his- togram modification framework and its application for image contrast enhancement.IEEE Transactions on image process- ing, 18(9):1921–1935, 2009. 2

    work page 1921

  3. [3]

    A 240 × 180 130 db 3 µs latency global shutter spatiotemporal vision sensor.IEEE Journal of Solid-State Circuits, 49(10):2333–2341, 2014

    Christian Brandli, Raphael Berner, Minhao Yang, Shih-Chii Liu, and Tobi Delbruck. A 240 × 180 130 db 3 µs latency global shutter spatiotemporal vision sensor.IEEE Journal of Solid-State Circuits, 49(10):2333–2341, 2014. 2, 6

    work page 2014

  4. [4]

    Retinexformer: One-stage retinex- based transformer for low-light image enhancement

    Yuanhao Cai, Hao Bian, Jing Lin, Haoqian Wang, Radu Tim- ofte, and Yulun Zhang. Retinexformer: One-stage retinex- based transformer for low-light image enhancement. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12504–12513, 2023. 1, 2, 3, 6, 7

    work page 2023

  5. [5]

    Learning robust event- guided representations for person re-identification: Cao et al

    Chengzhi Cao, Xueyang Fu, Senyan Xu, Chengjie Ge, Kunyu Wang, and Zheng-Jun Zha. Learning robust event- guided representations for person re-identification: Cao et al. International Journal of Computer Vision, 134(2):82, 2026. 2

    work page 2026

  6. [6]

    Physics-guided iso-dependent sensor noise modeling for extreme low-light photography

    Yue Cao, Ming Liu, Shuai Liu, Xiaotao Wang, Lei Lei, and Wangmeng Zuo. Physics-guided iso-dependent sensor noise modeling for extreme low-light photography. InProceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5744–5753, 2023. 5

    work page 2023

  7. [7]

    Qmambabsr: Burst image super-resolution with query state space model

    Xin Di, Long Peng, Peizhe Xia, Wenbo Li, Renjing Pei, Yang Cao, Yang Wang, and Zheng-Jun Zha. Qmambabsr: Burst image super-resolution with query state space model. InProceedings of the Computer Vision and Pattern Recogni- tion Conference, pages 23080–23090, 2025. 2

    work page 2025

  8. [8]

    An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

    Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Syl- vain Gelly, et al. An image is worth 16x16 words: Trans- formers for image recognition at scale.arXiv preprint arXiv:2010.11929, 2020. 2

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  9. [9]

    Led: A large-scale real-world paired dataset for event camera denoising

    Yuxing Duan. Led: A large-scale real-world paired dataset for event camera denoising. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 25637–25647, 2024. 2, 5

    work page 2024

  10. [10]

    Dancing in the dark: A benchmark towards general low-light video enhancement

    Huiyuan Fu, Wenkai Zheng, Xicong Wang, Jiaxuan Wang, Heng Zhang, and Huadong Ma. Dancing in the dark: A benchmark towards general low-light video enhancement. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12877–12886, 2023. 2

    work page 2023

  11. [11]

    A weighted variational model for simulta- neous reflectance and illumination estimation

    Xueyang Fu, Delu Zeng, Yue Huang, Xiao-Ping Zhang, and Xinghao Ding. A weighted variational model for simulta- neous reflectance and illumination estimation. InProceed- ings of the IEEE conference on computer vision and pattern recognition, pages 2782–2790, 2016. 2

    work page 2016

  12. [12]

    Event-driven heteroge- neous network for video deraining.International Journal of Computer Vision, 132(12):5841–5861, 2024

    Xueyang Fu, Chengzhi Cao, Senyan Xu, Fanrui Zhang, Kunyu Wang, and Zheng-Jun Zha. Event-driven heteroge- neous network for video deraining.International Journal of Computer Vision, 132(12):5841–5861, 2024. 2

    work page 2024

  13. [13]

    A unifying contrast maximization framework for event cam- eras, with applications to motion, depth, and optical flow estimation

    Guillermo Gallego, Henri Rebecq, and Davide Scaramuzza. A unifying contrast maximization framework for event cam- eras, with applications to motion, depth, and optical flow estimation. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 3867–3876,

    work page

  14. [14]

    Eventmamba: Enhancing spatio- temporal locality with state space models for event-based video reconstruction

    Chengjie Ge, Xueyang Fu, Peng He, Kunyu Wang, Chengzhi Cao, and Zheng-Jun Zha. Eventmamba: Enhancing spatio- temporal locality with state space models for event-based video reconstruction. InProceedings of the AAAI Confer- ence on Artificial Intelligence, pages 3104–3112, 2025. 2

    work page 2025

  15. [15]

    J-M Geusebroek, Rein Van den Boomgaard, Arnold W. M. Smeulders, and Hugo Geerts. Color invariance.IEEE Trans- actions on Pattern analysis and machine intelligence, 23 (12):1338–1350, 2001. 1, 2

    work page 2001

  16. [16]

    Mambair: A simple baseline for image restoration with state-space model

    Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, and Shu-Tao Xia. Mambair: A simple baseline for image restoration with state-space model. InEuropean con- ference on computer vision, pages 222–241. Springer, 2025. 1

    work page 2025

  17. [17]

    Low cost and latency event camera background activity denoising.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1):785– 795, 2022

    Shasha Guo and Tobi Delbruck. Low cost and latency event camera background activity denoising.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1):785– 795, 2022. 5

    work page 2022

  18. [18]

    Lime: Low-light im- age enhancement via illumination map estimation.IEEE Transactions on image processing, 26(2):982–993, 2016

    Xiaojie Guo, Yu Li, and Haibin Ling. Lime: Low-light im- age enhancement via illumination map estimation.IEEE Transactions on image processing, 26(2):982–993, 2016. 2

    work page 2016

  19. [19]

    Deep residual learning for image recognition

    Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. InProceed- ings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. 2

    work page 2016

  20. [20]

    Dslr-quality photos on mobile devices with deep convolutional networks

    Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Kenneth Vanhoey, and Luc Van Gool. Dslr-quality photos on mobile devices with deep convolutional networks. InProceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. 6

    work page 2017

  21. [21]

    Learning to see moving objects in the dark

    Haiyang Jiang and Yinqiang Zheng. Learning to see moving objects in the dark. InProceedings of the IEEE/CVF inter- national conference on computer vision, pages 7324–7333,

    work page

  22. [22]

    Rbsformer: En- hanced transformer network for raw image super-resolution

    Siyuan Jiang, Senyan Xu, and Xingfu Wang. Rbsformer: En- hanced transformer network for raw image super-resolution. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6479–6488, 2024. 2

    work page 2024

  23. [23]

    When fast fourier transform meets transformer for image restoration

    Xingyu Jiang, Xiuhui Zhang, Ning Gao, and Yue Deng. When fast fourier transform meets transformer for image restoration. InEuropean Conference on Computer Vision, pages 381–402. Springer, 2025. 6, 7

    work page 2025

  24. [24]

    Event-based low-illumination im- age enhancement.IEEE Transactions on Multimedia, 26: 1920–1931, 2024

    Yu Jiang, Yuehang Wang, Siqi Li, Yongji Zhang, Ming- hao Zhao, and Yue Gao. Event-based low-illumination im- age enhancement.IEEE Transactions on Multimedia, 26: 1920–1931, 2024. 1, 2, 3, 6, 7

    work page 1920

  25. [25]

    Towards real-world event-guided low- light video enhancement and deblurring

    Taewoo Kim, Jaeseok Jeong, Hoonhee Cho, Yuhwan Jeong, and Kuk-Jin Yoon. Towards real-world event-guided low- light video enhancement and deblurring. InEuropean Con- ference on Computer Vision, pages 433–451. Springer, 2025. 2

    work page 2025

  26. [26]

    Lookupvit: Compressing visual information to a limited number of tokens

    Rajat Koner, Gagan Jain, Prateek Jain, V olker Tresp, and Su- joy Paul. Lookupvit: Compressing visual information to a limited number of tokens. InEuropean Conference on Com- puter Vision, pages 322–337. Springer, 2025. 4

    work page 2025

  27. [27]

    Lightness and retinex theory.Josa, 61(1):1–11, 1971

    Edwin H Land and John J McCann. Lightness and retinex theory.Josa, 61(1):1–11, 1971. 1, 3

    work page 1971

  28. [28]

    Human pose estimation in extremely low-light condi- tions

    Sohyun Lee, Jaesung Rim, Boseung Jeong, Geonu Kim, Byungju Woo, Haechan Lee, Sunghyun Cho, and Suha Kwak. Human pose estimation in extremely low-light condi- tions. InProceedings of the IEEE/CVF conference on com- puter vision and pattern recognition, pages 704–714, 2023. 6

    work page 2023

  29. [29]

    Fouriermamba: Fourier learning integration with state space models for image deraining.arXiv preprint arXiv:2405.19450, 2024

    Dong Li, Yidi Liu, Xueyang Fu, Senyan Xu, and Zheng- Jun Zha. Fouriermamba: Fourier learning integration with state space models for image deraining.arXiv preprint arXiv:2405.19450, 2024. 2

    work page arXiv 2024

  30. [30]

    Towards robust event-guided low-light image enhancement: A large-scale real-world event-image dataset and novel approach

    Guoqiang Liang, Kanghao Chen, Hangyu Li, Yunfan Lu, and Lin Wang. Towards robust event-guided low-light image enhancement: A large-scale real-world event-image dataset and novel approach. InProceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition, pages 23–33, 2024. 1, 2, 3, 6, 7, 8

    work page 2024

  31. [31]

    Coherent event guided low-light video en- hancement

    Jinxiu Liang, Yixin Yang, Boyu Li, Peiqi Duan, Yong Xu, and Boxin Shi. Coherent event guided low-light video en- hancement. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 10615–10625, 2023. 2, 3, 6, 7

    work page 2023

  32. [32]

    Motion-adaptive separable collaborative filters for blind motion deblurring

    Chengxu Liu, Xuan Wang, Xiangyu Xu, Ruhao Tian, Shuai Li, Xueming Qian, and Ming-Hsuan Yang. Motion-adaptive separable collaborative filters for blind motion deblurring. In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition, pages 25595–25605, 2024. 5

    work page 2024

  33. [33]

    Design of a spatiotemporal correlation filter for event-based sensors

    Hongjie Liu, Christian Brandli, Chenghan Li, Shih-Chii Liu, and Tobi Delbruck. Design of a spatiotemporal correlation filter for event-based sensors. In2015 IEEE International Symposium on Circuits and Systems (ISCAS), pages 722–

    work page

  34. [34]

    Seeing motion at nighttime with an event camera

    Haoyue Liu, Shihan Peng, Lin Zhu, Yi Chang, Hanyu Zhou, and Luxin Yan. Seeing motion at nighttime with an event camera. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 25648– 25658, 2024. 1, 2, 6

    work page 2024

  35. [35]

    Event-conditioned dual-modal fusion for motion deblurring

    Kean Liu, Mingchen Zhong, Senyan Xu, Zhijing Sun, Jiay- ing Zhu, Chengjie Ge, Xingbo Wang, Xin Lu, Xueyang Fu, and Zheng-Jun Zha. Event-conditioned dual-modal fusion for motion deblurring. InProceedings of the Computer Vi- sion and Pattern Recognition Conference, pages 1482–1492,

    work page

  36. [36]

    Low-light video enhancement with synthetic event guidance

    Lin Liu, Junfeng An, Jianzhuang Liu, Shanxin Yuan, Xi- angyu Chen, Wengang Zhou, Houqiang Li, Yan Feng Wang, and Qi Tian. Low-light video enhancement with synthetic event guidance. InProceedings of the AAAI Conference on Artificial Intelligence, pages 1692–1700, 2023. 1, 2, 3, 6

    work page 2023

  37. [37]

    Dreamuhd: Frequency enhanced variational autoencoder for ultra-high-definition image restoration

    Yidi Liu, Dong Li, Jie Xiao, Yuanfei Bao, Senyan Xu, and Xueyang Fu. Dreamuhd: Frequency enhanced variational autoencoder for ultra-high-definition image restoration. In Proceedings of the AAAI Conference on Artificial Intelli- gence, pages 5712–5720, 2025. 2

    work page 2025

  38. [38]

    Ll- net: A deep autoencoder approach to natural low-light image enhancement.Pattern Recognition, 61:650–662, 2017

    Kin Gwn Lore, Adedotun Akintayo, and Soumik Sarkar. Ll- net: A deep autoencoder approach to natural low-light image enhancement.Pattern Recognition, 61:650–662, 2017. 2

    work page 2017

  39. [39]

    Evenformer: Dynamic even transformer for real- world image restoration

    Xin Lu, Yuanfei Bao, Jiarong Yang, Anya Hu, Jie Xiao, Kunyu Wang, Dong Li, Senyan Xu, Kean Liu, Xueyang Fu, et al. Evenformer: Dynamic even transformer for real- world image restoration. InProceedings of the Computer Vi- sion and Pattern Recognition Conference, pages 1081–1091,

    work page

  40. [40]

    Mbllen: Low-light image/video enhancement using cnns

    Feifan Lv, Feng Lu, Jianhua Wu, and Chongsoon Lim. Mbllen: Low-light image/video enhancement using cnns. In BMVC, page 4. Northumbria University, 2018. 2

    work page 2018

  41. [41]

    Color image contrast enhacement method based on differential in- tensity/saturation gray-levels histograms

    Keita Nakai, Yoshikatsu Hoshi, and Akira Taguchi. Color image contrast enhacement method based on differential in- tensity/saturation gray-levels histograms. In2013 Interna- tional Symposium on Intelligent Signal Processing and Com- munication Systems, pages 445–449. IEEE, 2013. 2

    work page 2013

  42. [42]

    Reparameterized multi-scale trans- former for deformable retinal image registration.Machine Intelligence Research, 22(3):524–538, 2025

    Qiushi Nie, Xiaoqing Zhang, Chuan Chen, Zhixuan Zhang, Yan Hu, and Jiang Liu. Reparameterized multi-scale trans- former for deformable retinal image registration.Machine Intelligence Research, 22(3):524–538, 2025. 2

    work page 2025

  43. [43]

    Video frame in- terpolation via adaptive separable convolution

    Simon Niklaus, Long Mai, and Feng Liu. Video frame in- terpolation via adaptive separable convolution. InProceed- ings of the IEEE international conference on computer vi- sion, pages 261–270, 2017. 5

    work page 2017

  44. [44]

    Boosting real-world super-resolution with raw data: a new perspective, dataset and baseline

    Long Peng, Wenbo Li, Jiaming Guo, Xin Di, Haoze Sun, Yong Li, Renjing Pei, Yang Wang, Yang Cao, and Zheng-Jun Zha. Boosting real-world super-resolution with raw data: a new perspective, dataset and baseline. 2

    work page

  45. [45]

    Efficient real-world image super-resolution via adaptive directional gradient convolution.arXiv preprint arXiv:2405.07023, 2024

    Long Peng, Yang Cao, Renjing Pei, Wenbo Li, Jiaming Guo, Xueyang Fu, Yang Wang, and Zheng-Jun Zha. Efficient real- world image super-resolution via adaptive directional gradi- ent convolution.arXiv preprint arXiv:2405.07023, 2024

    work page arXiv 2024

  46. [46]

    Lightweight adaptive feature de-drifting for compressed im- age classification.IEEE Transactions on Multimedia, 26: 6424–6436, 2024

    Long Peng, Yang Cao, Yuejin Sun, and Yang Wang. Lightweight adaptive feature de-drifting for compressed im- age classification.IEEE Transactions on Multimedia, 26: 6424–6436, 2024

    work page 2024

  47. [47]

    Unveiling hidden details: A raw data-enhanced paradigm for real-world super-resolution.arXiv preprint arXiv:2411.10798, 2024

    Long Peng, Wenbo Li, Jiaming Guo, Xin Di, Haoze Sun, Yong Li, Renjing Pei, Yang Wang, Yang Cao, and Zheng- Jun Zha. Unveiling hidden details: A raw data-enhanced paradigm for real-world super-resolution.arXiv preprint arXiv:2411.10798, 2024

    work page arXiv 2024

  48. [48]

    Towards real- istic data generation for real-world super-resolution.arXiv preprint arXiv:2406.07255, 2024

    Long Peng, Wenbo Li, Renjing Pei, Jingjing Ren, Jiaqi Xu, Yang Wang, Yang Cao, and Zheng-Jun Zha. Towards real- istic data generation for real-world super-resolution.arXiv preprint arXiv:2406.07255, 2024

    work page arXiv 2024

  49. [49]

    Directing mamba to complex textures: An effi- cient texture-aware state space model for image restoration

    Long Peng, Xin Di, Zhanfeng Feng, Wenbo Li, Renjing Pei, Yang Wang, Xueyang Fu, Yang Cao, and Zheng-Jun Zha. Directing mamba to complex textures: An efficient texture- aware state space model for image restoration.arXiv preprint arXiv:2501.16583, 2025

    work page arXiv 2025

  50. [50]

    Boosting image de-raining via central- surrounding synergistic convolution

    Long Peng, Yang Wang, Xin Di, Xueyang Fu, Yang Cao, Zheng-Jun Zha, et al. Boosting image de-raining via central- surrounding synergistic convolution. InProceedings of the AAAI Conference on Artificial Intelligence, pages 6470– 6478, 2025

    work page 2025

  51. [51]

    Pixel to gaussian: Ultra-fast continuous super-resolution with 2d gaussian modeling.arXiv preprint arXiv:2503.06617, 2025

    Long Peng, Anran Wu, Wenbo Li, Peizhe Xia, Xueyuan Dai, Xinjie Zhang, Xin Di, Haoze Sun, Renjing Pei, Yang Wang, et al. Pixel to gaussian: Ultra-fast continuous super-resolution with 2d gaussian modeling.arXiv preprint arXiv:2503.06617, 2025. 2

    work page arXiv 2025

  52. [52]

    You only look once: Unified, real-time object de- tection

    J Redmon. You only look once: Unified, real-time object de- tection. InProceedings of the IEEE conference on computer vision and pattern recognition, 2016. 1

    work page 2016

  53. [53]

    Learning separable filters

    Roberto Rigamonti, Amos Sironi, Vincent Lepetit, and Pas- cal Fua. Learning separable filters. InProceedings of the IEEE conference on computer vision and pattern recogni- tion, pages 2754–2761, 2013. 5

    work page 2013

  54. [54]

    Reducing the sim-to-real gap for event cameras

    Timo Stoffregen, Cedric Scheerlinck, Davide Scaramuzza, Tom Drummond, Nick Barnes, Lindsay Kleeman, and Robert Mahony. Reducing the sim-to-real gap for event cameras. InComputer Vision–ECCV 2020, pages 534–549. Springer, 2020. 6

    work page 2020

  55. [55]

    Low-light image enhancement using event-based illumination estimation

    Lei Sun, Yuhan Bao, Jiajun Zhai, Jingyun Liang, Yu- lun Zhang, Kaiwei Wang, Danda Pani Paudel, and Luc Van Gool. Low-light image enhancement using event-based illumination estimation. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 6667– 6677, 2025. 2

    work page 2025

  56. [56]

    Evdm: Event-based real-world video deblurring with mamba

    Zhijing Sun, Senyan Xu, Kean Liu, Runze Tian, Xueyang Fu, and Zheng-Jun Zha. Evdm: Event-based real-world video deblurring with mamba. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 13793–13803, 2025. 2

    work page 2025

  57. [57]

    Maxim: Multi-axis mlp for image processing

    Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, and Yinxiao Li. Maxim: Multi-axis mlp for image processing. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5769–5780, 2022. 1

    work page 2022

  58. [58]

    Attention is all you need.Advances in neural information processing systems, 30, 2017

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszko- reit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need.Advances in neural information processing systems, 30, 2017. 2

    work page 2017

  59. [59]

    Event enhanced high-quality image recovery

    Bishan Wang, Jingwei He, Lei Yu, Gui-Song Xia, and Wen Yang. Event enhanced high-quality image recovery. In Proceedings of the European conference on computer vision (ECCV), pages 155–171. Springer, 2020. 2, 6, 7

    work page 2020

  60. [60]

    Event- based high dynamic range image and very high frame rate video generation using conditional generative adversarial networks

    Lin Wang, Yo-Sung Ho, Kuk-Jin Yoon, et al. Event- based high dynamic range image and very high frame rate video generation using conditional generative adversarial networks. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10081– 10090, 2019. 4

    work page 2019

  61. [61]

    Seeing dynamic scene in the dark: A high-quality video dataset with mechatronic alignment

    Ruixing Wang, Xiaogang Xu, Chi-Wing Fu, Jiangbo Lu, Bei Yu, and Jiaya Jia. Seeing dynamic scene in the dark: A high-quality video dataset with mechatronic alignment. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9700–9709, 2021. 6, 8

    work page 2021

  62. [62]

    Unleashing the power of cnn and transformer for balanced rgb-event video recog- nition.Machine Intelligence Research, 22(6):1031–1047,

    Xiao Wang, Yao Rong, Shiao Wang, Yuan Chen, Zhe Wu, Bo Jiang, Yonghong Tian, and Jin Tang. Unleashing the power of cnn and transformer for balanced rgb-event video recog- nition.Machine Intelligence Research, 22(6):1031–1047,

    work page

  63. [63]

    Low-light image enhancement with illumination-aware gamma correction and complete image modelling network

    Yinglong Wang, Zhen Liu, Jianzhuang Liu, Songcen Xu, and Shuaicheng Liu. Low-light image enhancement with illumination-aware gamma correction and complete image modelling network. InProceedings of the IEEE/CVF In- ternational Conference on Computer Vision, pages 13128– 13137, 2023. 2

    work page 2023

  64. [64]

    Uformer: A general u-shaped transformer for image restoration

    Zhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou, Jianzhuang Liu, and Houqiang Li. Uformer: A general u-shaped transformer for image restoration. InProceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 17683–17693, 2022. 1, 2, 6

    work page 2022

  65. [65]

    Deep Retinex Decomposition for Low-Light Enhancement

    Chen Wei, Wenjing Wang, Wenhan Yang, and Jiaying Liu. Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560, 2018. 2, 3

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  66. [66]

    Event-based image enhancement under high dynamic range scenarios

    Jingchong Weng, Boyang Li, and Kai Huang. Event-based image enhancement under high dynamic range scenarios. In Proceedings of the Asian Conference on Computer Vision, pages 2456–2470, 2024. 2

    work page 2024

  67. [67]

    Mamballie: Implicit retinex-aware low light enhancement with global-then-local state space

    Jiangwei Weng, Zhiqiang Yan, Ying Tai, Jianjun Qian, Jian Yang, and Jun Li. Mamballie: Implicit retinex-aware low light enhancement with global-then-local state space. InAd- vances in neural information processing systems, 2024. 1, 2, 4, 6, 7

    work page 2024

  68. [68]

    Simple online and realtime tracking with a deep association metric

    Nicolai Wojke, Alex Bewley, and Dietrich Paulus. Simple online and realtime tracking with a deep association metric. In2017 IEEE international conference on image processing (ICIP), pages 3645–3649. IEEE, 2017. 1

    work page 2017

  69. [69]

    Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement

    Wenhui Wu, Jian Weng, Pingping Zhang, Xu Wang, Wen- han Yang, and Jianmin Jiang. Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement. InProceedings of the IEEE/CVF conference on computer vi- sion and pattern recognition, pages 5901–5910, 2022. 2, 3

    work page 2022

  70. [70]

    Learning semantic-aware knowledge guidance for low-light image enhancement

    Yuhui Wu, Chen Pan, Guoqing Wang, Yang Yang, Jiwei Wei, Chongyi Li, and Heng Tao Shen. Learning semantic-aware knowledge guidance for low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition, pages 1662–1671, 2023. 2, 6

    work page 2023

  71. [71]

    Image de-raining transformer.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11):12978– 12995, 2022

    Jie Xiao, Xueyang Fu, Aiping Liu, Feng Wu, and Zheng-Jun Zha. Image de-raining transformer.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11):12978– 12995, 2022. 2

    work page 2022

  72. [72]

    Bayesian window transformer for image restoration.IEEE Transactions on Pattern Analysis and Machine Intelligence,

    Jie Xiao, Xueyang Fu, Yurui Zhu, and Zheng-Jun Zha. Bayesian window transformer for image restoration.IEEE Transactions on Pattern Analysis and Machine Intelligence,

    work page

  73. [73]

    Star: A struc- ture and texture aware retinex model.IEEE Transactions on Image Processing, 29:5022–5037, 2020

    Jun Xu, Yingkun Hou, Dongwei Ren, Li Liu, Fan Zhu, Mengyang Yu, Haoqian Wang, and Ling Shao. Star: A struc- ture and texture aware retinex model.IEEE Transactions on Image Processing, 29:5022–5037, 2020. 2

    work page 2020

  74. [74]

    Demosaicformer: Coarse-to-fine de- mosaicing network for hybridevs camera

    Senyan Xu, Zhijing Sun, Jiaying Zhu, Yurui Zhu, Xueyang Fu, and Zheng-Jun Zha. Demosaicformer: Coarse-to-fine de- mosaicing network for hybridevs camera. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1126–1135, 2024. 2

    work page 2024

  75. [75]

    Motion-adaptive trans- former for event-based image deblurring

    Senyan Xu, Zhijing Sun, Mingchen Zhong, Chengzhi Cao, Yidi Liu, Xueyang Fu, and Yan Chen. Motion-adaptive trans- former for event-based image deblurring. InProceedings of the AAAI Conference on Artificial Intelligence, pages 8942– 8950, 2025. 2

    work page 2025

  76. [76]

    Snr-aware low-light image enhancement

    Xiaogang Xu, Ruixing Wang, Chi-Wing Fu, and Jiaya Jia. Snr-aware low-light image enhancement. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 17714–17724, 2022. 6

    work page 2022

  77. [77]

    Restormer: Efficient transformer for high-resolution image restoration

    Syed Waqas Zamir, Aditya Arora, Salman Khan, Mu- nawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. Restormer: Efficient transformer for high-resolution image restoration. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5728–5739,

    work page

  78. [78]

    Learning to see in the dark with events

    Song Zhang, Yu Zhang, Zhe Jiang, Dongqing Zou, Jimmy Ren, and Bin Zhou. Learning to see in the dark with events. InComputer Vision–ECCV 2020: 16th European Confer- ence, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVIII 16, pages 666–682. Springer, 2020. 1, 2, 3

    work page 2020

  79. [79]

    Kindling the darkness: A practical low-light image enhancer

    Yonghua Zhang, Jiawan Zhang, and Xiaojie Guo. Kindling the darkness: A practical low-light image enhancer. InPro- ceedings of the 27th ACM international conference on mul- timedia, pages 1632–1640, 2019. 2, 3

    work page 2019

  80. [80]

    Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers

    Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip HS Torr, et al. Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6881–6890,

    work page

Showing first 80 references.