pith. sign in

arxiv: 2606.13580 · v1 · pith:GPYMOTUKnew · submitted 2026-06-11 · 💻 cs.CV · cs.AI

EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution

Dachun Kai , Jiayao Lu , Yueyi Zhang , Xiaoyan Sun This is my paper

Pith reviewed 2026-06-27 07:04 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords event-based visionvideo super-resolutiontexture enhancementtemporal alignmentplug-and-playhigh-frequency detailsevent cameras
0
0 comments X

The pith

Event signals can be redirected from motion to texture enhancement for better video super-resolution.

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

The paper proposes EvTexture++, a framework that uses high-frequency details from event signals specifically to restore textures in video super-resolution instead of refining motion estimates. It adds a texture enhancement branch and an iterative module that refines textures gradually across steps by drawing on the high temporal resolution of events. A temporal alignment module uses continuous event motion cues to align textures between frames and reduce flickering. The whole system is built as a plug-and-play addition to existing video super-resolution models. A reader would care because it promises sharper textures and more stable results in high-resolution video without replacing current approaches.

Core claim

EvTexture++ is the first event-driven framework dedicated to texture enhancement in VSR. It leverages high-frequency spatiotemporal details from events to improve texture recovery. EvTexture++ incorporates a customized texture enhancement branch, along with an iterative texture enhancement module that progressively exploits high-temporal-resolution event information for texture restoration. This enables gradual refinement of texture regions across iterations, yielding more accurate and detailed high-resolution outputs. Besides intra-frame texture recovery, large motions could degrade inter-frame temporal consistency, particularly in texture regions, leading to texture flickering. To mitigate

What carries the argument

The iterative texture enhancement module that progressively exploits high-temporal-resolution event information, paired with the temporal texture alignment module using event-guided texture-aware flow.

If this is right

  • Existing VSR models receive consistent performance gains when the framework is added as a plug-in.
  • Texture regions in the output videos recover more accurate high-frequency details.
  • Inter-frame alignment reduces flickering in moving textured areas.
  • The method applies across multiple datasets while remaining flexible for different base models.

Where Pith is reading between the lines

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

  • Event sensors might support detail recovery in related video tasks such as denoising or frame interpolation.
  • The iterative refinement pattern could be adapted to other sensor types that provide high-temporal data.
  • Real-world tests on raw event streams with varying motion speeds would show whether the alignment holds without extra calibration.

Load-bearing premise

High-frequency spatiotemporal details from event signals can be directly and progressively used for texture restoration and alignment without introducing new artifacts.

What would settle it

Integrating EvTexture++ into a recent VSR model and measuring PSNR on the Vid4 dataset; absence of the reported gain or a drop in performance would falsify the improvement claim.

Figures

Figures reproduced from arXiv: 2606.13580 by Dachun Kai, Jiayao Lu, Xiaoyan Sun, Yueyi Zhang.

Figure 1
Figure 1. Figure 1: Performance versus runtime on Vid4 [1]. The circle size corresponds to the number of parameters. Our EvTexture++ achieves a superior trade-off between performance and efficiency. Notably, equipping the state-of-the-art RGB-based VSR model IART [2] with our EvTexture++ plug-in yields a remarkable gain of ∼1.55 dB. Runtime is measured on 180 × 320 LR inputs. Over the past few years, VSR approaches have progr… view at source ↗
Figure 2
Figure 2. Figure 2: Visual comparison on a challenging texture-rich scene. While current VSR methods, whether frame-based ( [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Visual comparison of the plug-in effectiveness on the state-of-the [PITH_FULL_IMAGE:figures/full_fig_p002_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Comparison of different VSR paradigms. (a) RGB-based methods [PITH_FULL_IMAGE:figures/full_fig_p003_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Network architecture of EvTexture++. (a) EvTexture++ adopts a bidirectional recurrent structure with parallel event-guided texture and motion branches [PITH_FULL_IMAGE:figures/full_fig_p004_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Event-guided Motion Branch in EvTexture++. (a) EvTexture++ further integrates event signals into the motion branch and introduces a Temporal [PITH_FULL_IMAGE:figures/full_fig_p006_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Overview of the EvTexture++ plug-in framework. During training, the frozen backbone extracts three types of features: spatial features before b [PITH_FULL_IMAGE:figures/full_fig_p007_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Qualitative comparison on Vid4 [1] for 4× VSR. Only EvTexture++ can restore vivid branches and leaves on the tulip tree [PITH_FULL_IMAGE:figures/full_fig_p010_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Qualitative comparison on Vimeo-90K-T [6] for 4× VSR. Only EvTexture++ can restore faithful and detailed stripes on clothing surfaces. Vid4, consistently improving across all clips, as well as an additional 0.16 dB gain on REDS4. Furthermore, as detailed in Tab. V, EvTexture++ attains the lowest LPIPS score of 0.2048 on Vid4, demonstrating superior perceptual quality. Qualitative comparisons on Vid4, Vimeo… view at source ↗
Figure 10
Figure 10. Figure 10: Qualitative comparison on REDS4 [55] for 4× VSR. Only EvTexture++ can clearly recover the digits “5886” on the license plate [PITH_FULL_IMAGE:figures/full_fig_p011_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Qualitative comparison on UDM10 [58] for 8× VSR. Only EvTexture++ can restore fine details such as camera text and railings [PITH_FULL_IMAGE:figures/full_fig_p011_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Qualitative comparison on CED [60] for 4× VSR. Only EvTexture++ can recover fine wall textures and sharp facial details. both datasets, yielding lower tOF [70] and higher TCC [71] scores than all other methods. To further illustrate stability, [PITH_FULL_IMAGE:figures/full_fig_p011_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Visual comparison of BasicVSR++[8], PSRT[22], MIA-VSR [10], and IART [2] before and after being equipped with our plug-in EvTexture++ (††) . The PSNR values are indicated in the images. Our EvTexture++ plug-in significantly improves restoration, producing clearer textures and more visual details. models suffer from per-frame latency exceeding 1000 ms. Compared to EBVSR [16] (12.16M parameters), EvTexture+… view at source ↗
Figure 16
Figure 16. Figure 16: PSNR during training on REDS4 [55] for 4× VSR using IART-based plug-in variants. IART [2] achieves 32.90 dB as reference. ∗ shows similar parameters as EvTexture++. EvTexture++ significantly improves performance. TABLE VII ABLATION STUDY OF TEXTURE AND MOTION BRANCHES. Model Vid4 [1] REDS4 [55] Params(M) Base 27.44/0.8284 31.58/0.8932 6.29 Base + Texture 29.51/0.8909 32.79/0.9174 8.90 Base + Motion 28.22/… view at source ↗
Figure 15
Figure 15. Figure 15: Comparison of temporal profiles. We track a fixed column over time. [PITH_FULL_IMAGE:figures/full_fig_p013_15.png] view at source ↗
Figure 19
Figure 19. Figure 19: Visual results of the iterative texture enhancement process. As the [PITH_FULL_IMAGE:figures/full_fig_p014_19.png] view at source ↗
Figure 20
Figure 20. Figure 20: Texture magnitude analysis of five datasets. The results reveal that [PITH_FULL_IMAGE:figures/full_fig_p014_20.png] view at source ↗
Figure 21
Figure 21. Figure 21: Pixel movement distributions of the REDS4 [PITH_FULL_IMAGE:figures/full_fig_p016_21.png] view at source ↗
read the original abstract

Event-based vision has drawn increasing attention owing to its distinctive properties, including ultra-high temporal resolution and extreme dynamic range. Recent works have introduced it to video super-resolution (VSR) to enhance flow estimation and temporal alignment. In contrast, this paper shifts the focus of event signals from motion refinement to texture enhancement in VSR. We propose EvTexture++, the first event-driven framework dedicated to texture enhancement in VSR. It leverages high-frequency spatiotemporal details from events to improve texture recovery. EvTexture++ incorporates a customized texture enhancement branch, along with an iterative texture enhancement module that progressively exploits high-temporal-resolution event information for texture restoration. This enables gradual refinement of texture regions across iterations, yielding more accurate and detailed high-resolution outputs. Besides intra-frame texture recovery, large motions could degrade inter-frame temporal consistency, particularly in texture regions, leading to texture flickering. To mitigate this, we further exploit the continuous-time motion cues of events to enhance temporal consistency, introducing a temporal texture alignment module that estimates event-guided texture-aware flow for precise inter-frame texture alignment. Moreover, EvTexture++ is designed as a plug-and-play tool to flexibly boost the performance of existing VSR models. Experiments on five datasets demonstrate that EvTexture++ achieves state-of-the-art performance. When integrated into recent VSR models, it yields significant improvements, with gains of up to 1.55 dB in PSNR on the texture-rich Vid4 dataset. Code: https://github.com/DachunKai/EvTexture.

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

0 major / 3 minor

Summary. The paper proposes EvTexture++, the first event-driven framework for texture enhancement in video super-resolution (VSR). It introduces a customized texture enhancement branch, an iterative texture enhancement module that progressively refines textures using high-temporal-resolution event data, and a temporal texture alignment module that uses event-guided texture-aware flow to mitigate texture flickering from large motions. The framework is designed as plug-and-play for integration into existing VSR models. Experiments on five datasets show state-of-the-art performance, with reported PSNR gains of up to 1.55 dB on the texture-rich Vid4 dataset when integrated into recent VSR models. Code is provided at https://github.com/DachunKai/EvTexture.

Significance. If the reported gains are supported by the architecture and controls, the work is significant for shifting event-based VSR from motion refinement to texture recovery, exploiting the ultra-high temporal resolution and dynamic range of event cameras for detailed high-resolution outputs and temporal consistency. The plug-and-play design and public code enable reproducibility and easy adoption, which strengthens the potential impact in practical video enhancement applications.

minor comments (3)
  1. [Abstract] Abstract and §1: The claim that EvTexture++ is 'the first event-driven framework dedicated to texture enhancement in VSR' would benefit from an explicit comparison table or paragraph distinguishing it from prior event-based VSR works focused on flow estimation.
  2. [Experiments] §4 (Experiments): The reported PSNR gains (e.g., 1.55 dB on Vid4) should include the specific baseline VSR models used for integration and whether event-free ablations of the proposed modules were performed to isolate the contribution of the texture enhancement branch.
  3. [Experiments] Figure 3 or equivalent (qualitative results): The visual comparisons would be clearer with zoomed-in insets highlighting texture regions before and after the iterative module and temporal alignment.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary, recognition of significance, and recommendation of minor revision. The referee's description accurately reflects the paper's focus on shifting event-based VSR toward texture enhancement, the proposed modules, plug-and-play design, and reported gains. No major comments were listed in the report, so we have no specific points requiring response or revision.

Circularity Check

0 steps flagged

No significant circularity; empirical architecture with reported gains

full rationale

The paper introduces EvTexture++ as a plug-and-play architecture comprising a texture enhancement branch, iterative module, and event-guided flow module. Claims rest on experimental integration into existing VSR models and measured PSNR/SSIM gains across five datasets (up to 1.55 dB on Vid4). No equations, first-principles derivations, or predictions that reduce to fitted inputs or self-citations are present in the provided text. The central results are externally falsifiable via the linked code and dataset benchmarks, making the work self-contained without circular reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review; no free parameters, axioms, or invented entities can be identified from the provided text.

pith-pipeline@v0.9.1-grok · 5806 in / 1164 out tokens · 19737 ms · 2026-06-27T07:04:56.084010+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

77 extracted references

  1. [1]

    On Bayesian adaptive video super resolution,

    C. Liu and D. Sun, “On Bayesian adaptive video super resolution,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 36, no. 2, pp. 346–360, 2013

    2013

  2. [2]

    Enhancing video super-resolution via implicit resampling-based alignment,

    K. Xu, Z. Yu, X. Wang, M. B. Mi, and A. Yao, “Enhancing video super-resolution via implicit resampling-based alignment,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2024, pp. 2546–2555

    2024

  3. [3]

    Super- resolution system for 4k-hdtv,

    T. Goto, T. Fukuoka, F. Nagashima, S. Hirano, and M. Sakurai, “Super- resolution system for 4k-hdtv,” inProc. IEEE Int. Conf. Pattern Recogn., 2014, pp. 4453–4458

    2014

  4. [4]

    A super-resolution reconstruc- tion algorithm for surveillance images,

    L. Zhang, H. Zhang, H. Shen, and P. Li, “A super-resolution reconstruc- tion algorithm for surveillance images,”Signal Processing, vol. 90, no. 3, pp. 848–859, 2010. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 48, NO. 6, JUNE 2026 17

    2010

  5. [5]

    A single frame and multi-frame joint network for 360- degree panorama video super-resolution,

    H. Liu, W. Ma, Z. Ruan, C. Fang, F. Shang, Y . Liu, L. Wang, C. Wang, and D. Jiang, “A single frame and multi-frame joint network for 360- degree panorama video super-resolution,”Engineering Applications of Artificial Intelligence, vol. 134, Art. no. 108601, 2024

    2024

  6. [6]

    Video enhancement with task-oriented flow,

    T. Xue, B. Chen, J. Wu, D. Wei, and W. T. Freeman, “Video enhancement with task-oriented flow,”Int. J. Comput. Vis., vol. 127, pp. 1106–1125, 2019

    2019

  7. [7]

    BasicVSR: The search for essential components in video super-resolution and beyond,

    K. C. Chan, X. Wang, K. Yu, C. Dong, and C. C. Loy, “BasicVSR: The search for essential components in video super-resolution and beyond,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2021, pp. 4947–4956

    2021

  8. [8]

    BasicVSR++: Improving video super-resolution with enhanced propagation and alignment,

    K. C. Chan, S. Zhou, X. Xu, and C. C. Loy, “BasicVSR++: Improving video super-resolution with enhanced propagation and alignment,” in Proc. IEEE Conf. Comput. Vis. Pattern Recogn., 2022, pp. 5972–5981

    2022

  9. [9]

    Cycmunet+: Cycle- projected mutual learning for spatial-temporal video super-resolution,

    M. Hu, K. Jiang, Z. Wang, X. Bai, and R. Hu, “Cycmunet+: Cycle- projected mutual learning for spatial-temporal video super-resolution,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 11, pp. 13 376– 13 392, 2023

    2023

  10. [10]

    Video super- resolution transformer with masked inter&intra-frame attention,

    X. Zhou, L. Zhang, X. Zhao, K. Wang, L. Li, and S. Gu, “Video super- resolution transformer with masked inter&intra-frame attention,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2024, pp. 25 399–25 408

    2024

  11. [11]

    Self-supervised deep blind video super-resolution,

    H. Bai and J. Pan, “Self-supervised deep blind video super-resolution,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 7, pp. 4641–4653, 2024

    2024

  12. [12]

    EDVR: Video restoration with enhanced deformable convolutional networks,

    X. Wang, K. C. Chan, K. Yu, C. Dong, and C. Change Loy, “EDVR: Video restoration with enhanced deformable convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recogn. Workshop, 2019, pp. 1954–1963

    2019

  13. [13]

    A 128×128 120 db 15 µs latency asynchronous temporal contrast vision sensor,

    P. Lichtsteiner, C. Posch, and T. Delbruck, “A 128×128 120 db 15 µs latency asynchronous temporal contrast vision sensor,”IEEE journal of solid-state circuits, vol. 43, no. 2, pp. 566–576, 2008

    2008

  14. [14]

    Turning frequency to resolution: Video super-resolution via event cameras,

    Y . Jing, Y . Yang, X. Wang, M. Song, and D. Tao, “Turning frequency to resolution: Video super-resolution via event cameras,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2021, pp. 7772–7781

    2021

  15. [15]

    Learning Spatial- Temporal Implicit Neural Representations for Event-Guided Video Super- Resolution,

    Y . Lu, Z. Wang, M. Liu, H. Wang, and L. Wang, “Learning Spatial- Temporal Implicit Neural Representations for Event-Guided Video Super- Resolution,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2023, pp. 1557–1567

    2023

  16. [16]

    Video Super-Resolution Via Event-Driven Temporal Alignment,

    D. Kai, Y . Zhang, and X. Sun, “Video Super-Resolution Via Event-Driven Temporal Alignment,” inProc. IEEE Int. Conf. Image Process.IEEE, 2023, pp. 2950–2954

    2023

  17. [17]

    EvTexture: Event-driven Texture Enhancement for Video Super-Resolution,

    D. Kai, J. Lu, Y . Zhang, and X. Sun, “EvTexture: Event-driven Texture Enhancement for Video Super-Resolution,” inInt. Conf. Mach. Learn., vol. 235. PMLR, 2024, pp. 22 817–22 839

    2024

  18. [18]

    Event- based vision: A survey,

    G. Gallego, T. Delbr ¨uck, G. Orchard, C. Bartolozzi, B. Taba, A. Censi, S. Leutenegger, A. J. Davison, J. Conradt, K. Daniilidiset al., “Event- based vision: A survey,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 1, pp. 154–180, 2020

    2020

  19. [19]

    TDPN: Texture and detail-preserving network for single image super-resolution,

    Q. Cai, J. Li, H. Li, Y .-H. Yang, F. Wu, and D. Zhang, “TDPN: Texture and detail-preserving network for single image super-resolution,”IEEE Trans. Image Process., vol. 31, pp. 2375–2389, 2022

    2022

  20. [20]

    CTE-Net: Contextual Texture Enhancement Network for Image Super-Resolution,

    D. Liu, X. Wang, R. Han, N. Bai, J. Hou, and S. Pang, “CTE-Net: Contextual Texture Enhancement Network for Image Super-Resolution,” IEEE Trans. Multimedia, 2024

    2024

  21. [21]

    Egovsr: Toward high- quality egocentric video super-resolution,

    Y . Chi, J. Gu, J. Zhang, W. Yang, and Y . Tian, “Egovsr: Toward high- quality egocentric video super-resolution,”IEEE Trans. Circuits Syst. Video Technol., vol. 34, no. 11, pp. 11 838–11 850, 2024

    2024

  22. [22]

    Rethinking alignment in video super-resolution transformers,

    S. Shi, J. Gu, L. Xie, X. Wang, Y . Yang, and C. Dong, “Rethinking alignment in video super-resolution transformers,”Proc. Adv. Neural Inf. Process. Syst., vol. 35, pp. 36 081–36 093, 2022

    2022

  23. [23]

    Unifying low- resolution and high-resolution alignment by event cameras for space-time video super-resolution,

    H. Cho, J.-Y . Kang, T. Kim, Y . Jeong, and K.-J. Yoon, “Unifying low- resolution and high-resolution alignment by event cameras for space-time video super-resolution,” inProc. Winter Conf. Appl. Comput. Vis.IEEE, 2025, pp. 9509–9520

    2025

  24. [24]

    VRT: A Video Restoration Transformer,

    J. Liang, J. Cao, Y . Fan, K. Zhang, R. Ranjan, Y . Li, R. Timofte, and L. Van Gool, “VRT: A Video Restoration Transformer,”IEEE Trans. Image Process., vol. 33, pp. 2171–2182, 2024

    2024

  25. [25]

    Learning degradation- robust spatiotemporal frequency-transformer for video super-resolution,

    Z. Qiu, H. Yang, J. Fu, D. Liu, C. Xu, and D. Fu, “Learning degradation- robust spatiotemporal frequency-transformer for video super-resolution,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 12, pp. 14 888– 14 904, 2023

    2023

  26. [26]

    ESRGAN: Enhanced super-resolution generative adversarial networks,

    X. Wang, K. Yu, S. Wu, J. Gu, Y . Liu, C. Dong, Y . Qiao, and C. Change Loy, “ESRGAN: Enhanced super-resolution generative adversarial networks,” inProc. Eur. Conf. Comput. Vis. Workshop, 2018, pp. 63–79

    2018

  27. [27]

    Attention is all you need,

    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,”Proc. Adv. Neural Inf. Process. Syst., vol. 30, pp. 5998–6008, 2017

    2017

  28. [28]

    SwinIR: Image restoration using swin transformer,

    J. Liang, J. Cao, G. Sun, K. Zhang, L. Van Gool, and R. Timofte, “SwinIR: Image restoration using swin transformer,” inProc. IEEE Int. Conf. Comput. Vis. Workshop, 2021, pp. 1833–1844

    2021

  29. [29]

    RAFT: Recurrent All-pairs Field Transforms for optical flow,

    Z. Teed and J. Deng, “RAFT: Recurrent All-pairs Field Transforms for optical flow,” inProc. Eur. Conf. Comput. Vis., 2020, pp. 402–419

    2020

  30. [30]

    Deformable convolutional networks,

    J. Dai, H. Qi, Y . Xiong, Y . Li, G. Zhang, H. Hu, and Y . Wei, “Deformable convolutional networks,” inProc. IEEE Int. Conf. Comput. Vis., 2017, pp. 764–773

    2017

  31. [31]

    Secrets of event-based optical flow, depth and ego-motion estimation by contrast maximization,

    S. Shiba, Y . Klose, Y . Aoki, and G. Gallego, “Secrets of event-based optical flow, depth and ego-motion estimation by contrast maximization,” IEEE Trans. Pattern Anal. Mach. Intell., 2024

    2024

  32. [32]

    Superfast: 200× video frame interpolation via event camera,

    Y . Gao, S. Li, Y . Li, Y . Guo, and Q. Dai, “Superfast: 200× video frame interpolation via event camera,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 6, pp. 7764–7780, 2022

    2022

  33. [33]

    Ner-net+: Seeing motion at nighttime with an event camera,

    H. Liu, J. Xu, S. Peng, Y . Chang, H. Zhou, Y . Duan, L. Zhu, Y . Tian, and L. Yan, “Ner-net+: Seeing motion at nighttime with an event camera,” IEEE Trans. Pattern Anal. Mach. Intell., 2025

    2025

  34. [34]

    Hybrid high dynamic range imaging fusing neuromorphic and conventional images,

    J. Han, Y . Yang, P. Duan, C. Zhou, L. Ma, C. Xu, T. Huang, I. Sato, and B. Shi, “Hybrid high dynamic range imaging fusing neuromorphic and conventional images,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 7, pp. 8553–8565, 2023

    2023

  35. [35]

    A unified framework for event-based frame interpolation with ad-hoc deblurring in the wild,

    L. Sun, D. Gehrig, C. Sakaridis, M. Gehrig, J. Liang, P. Sun, Z. Xu, K. Wang, L. Van Gool, and D. Scaramuzza, “A unified framework for event-based frame interpolation with ad-hoc deblurring in the wild,”IEEE Trans. Pattern Anal. Mach. Intell., 2024

    2024

  36. [36]

    Eventaid: Benchmarking event-aided image/video enhancement algorithms with real-captured hybrid dataset,

    P. Duan, B. Li, Y . Yang, H. Lou, M. Teng, X. Zhou, Y . Ma, and B. Shi, “Eventaid: Benchmarking event-aided image/video enhancement algorithms with real-captured hybrid dataset,”IEEE Trans. Pattern Anal. Mach. Intell., 2025

    2025

  37. [37]

    Event- adapted video super-resolution,

    Z. Xiao, D. Kai, Y . Zhang, Z.-J. Zha, X. Sun, and Z. Xiong, “Event- adapted video super-resolution,” inProc. Eur. Conf. Comput. Vis., 2024, pp. 217–235

    2024

  38. [38]

    Event- enhanced blurry video super-resolution,

    D. Kai, Y . Zhang, J. Wang, Z. Xiao, Z. Xiong, and X. Sun, “Event- enhanced blurry video super-resolution,” inProc. AAAI Conf. Artificial Intell., vol. 39, no. 4, 2025, pp. 4175–4183

    2025

  39. [39]

    Event-based video super-resolution via state space models,

    Z. Xiao and X. Wang, “Event-based video super-resolution via state space models,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., June 2025, pp. 12 564–12 574

    2025

  40. [40]

    Seeing the unseen: Zooming in the dark with event cameras,

    D. Kai, Z. Xiao, H. Zhu, J. Wang, Y . Zhang, and X. Sun, “Seeing the unseen: Zooming in the dark with event cameras,” inProc. AAAI Conf. Artificial Intell., 2026

    2026

  41. [41]

    Vision mamba: Efficient visual representation learning with bidirectional state space model,

    L. Zhu, B. Liao, Q. Zhang, X. Wang, W. Liu, and X. Wang, “Vision mamba: Efficient visual representation learning with bidirectional state space model,” inInt. Conf. Mach. Learn., vol. 235. PMLR, 2024, pp. 62 429–62 442

    2024

  42. [42]

    Evstvsr: Event guided space-time video super-resolution,

    H. Yan, Z. Lu, Z. Chen, D. Ma, H. Tang, Q. Zheng, and G. Pan, “Evstvsr: Event guided space-time video super-resolution,” inProc. AAAI Conf. Artificial Intell., vol. 39, no. 9, 2025, pp. 9085–9093

    2025

  43. [43]

    Local texture pattern estimation for image detail super-resolution,

    F. Fan, Y . Zhao, Y . Chen, N. Li, W. Jia, and R. Wang, “Local texture pattern estimation for image detail super-resolution,”IEEE Trans. Pattern Anal. Mach. Intell., 2025

    2025

  44. [44]

    Unsupervised event- based learning of optical flow, depth, and egomotion,

    A. Z. Zhu, L. Yuan, K. Chaney, and K. Daniilidis, “Unsupervised event- based learning of optical flow, depth, and egomotion,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2019, pp. 989–997

    2019

  45. [45]

    Learning dense and continuous optical flow from an event camera,

    Z. Wan, Y . Dai, and Y . Mao, “Learning dense and continuous optical flow from an event camera,”IEEE Trans. Image Process., vol. 31, pp. 7237–7251, 2022

    2022

  46. [46]

    EventGAN: Leveraging large scale image datasets for event cameras,

    A. Z. Zhu, Z. Wang, K. Khant, and K. Daniilidis, “EventGAN: Leveraging large scale image datasets for event cameras,” inProc. IEEE Int. Conf. Comput. Photography. IEEE, 2021, pp. 1–11

    2021

  47. [47]

    Real-time single image and video super- resolution using an efficient sub-pixel convolutional neural network,

    W. Shi, J. Caballero, F. Husz ´ar, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert, and Z. Wang, “Real-time single image and video super- resolution using an efficient sub-pixel convolutional neural network,” in Proc. IEEE Conf. Comput. Vis. Pattern Recogn., 2016, pp. 1874–1883

    2016

  48. [48]

    U-Net: Convolutional networks for biomedical image segmentation,

    O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” inProc. Int. Conf. Med. Image Comput. Comput. Assist. Interv., 2015, pp. 234–241

    2015

  49. [49]

    Super SloMo: High Quality Estimation of Multiple Intermedi- ate Frames for Video Interpolation,

    H. Jiang, D. Sun, V . Jampani, M.-H. Yang, E. Learned-Miller, and J. Kautz, “Super SloMo: High Quality Estimation of Multiple Intermedi- ate Frames for Video Interpolation,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2018, pp. 9000–9008

    2018

  50. [50]

    Optical flow estimation using a spatial pyramid network,

    A. Ranjan and M. J. Black, “Optical flow estimation using a spatial pyramid network,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2017, pp. 4161–4170

    2017

  51. [51]

    Delving deeper into convolutional networks for learning video representations,

    N. Ballas, L. Yao, C. Pal, and A. Courville, “Delving deeper into convolutional networks for learning video representations,” inProc. Int. Conf. Learn. Repr., 2016, pp. 1–12. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 48, NO. 6, JUNE 2026 18

    2016

  52. [52]

    Dense continuous-time optical flow from event cameras,

    M. Gehrig, M. Muglikar, and D. Scaramuzza, “Dense continuous-time optical flow from event cameras,”IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 7, pp. 4736–4746, 2024

    2024

  53. [53]

    Time lens: Event-based video frame interpolation,

    S. Tulyakov, D. Gehrig, S. Georgoulis, J. Erbach, M. Gehrig, Y . Li, and D. Scaramuzza, “Time lens: Event-based video frame interpolation,” in Proc. IEEE Conf. Comput. Vis. Pattern Recogn., 2021, pp. 16 155–16 164

    2021

  54. [54]

    Spatial transformer networks,

    M. Jaderberg, K. Simonyan, A. Zissermanet al., “Spatial transformer networks,”Proc. Adv. Neural Inf. Process. Syst., vol. 28, pp. 2017–2025, 2015

    2017

  55. [55]

    Ntire 2019 challenge on video deblurring and super-resolution: Dataset and study,

    S. Nah, S. Baik, S. Hong, G. Moon, S. Son, R. Timofte, and K. Mu Lee, “Ntire 2019 challenge on video deblurring and super-resolution: Dataset and study,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn. Workshop, 2019, pp. 1996–2005

    2019

  56. [56]

    Revisiting temporal alignment for video restoration,

    K. Zhou, W. Li, L. Lu, X. Han, and J. Lu, “Revisiting temporal alignment for video restoration,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2022, pp. 6053–6062

    2022

  57. [57]

    Recurrent video restoration transformer with guided deformable attention,

    J. Liang, Y . Fan, X. Xiang, R. Ranjan, E. Ilg, S. Green, J. Cao, K. Zhang, R. Timofte, and L. V . Gool, “Recurrent video restoration transformer with guided deformable attention,”Proc. Adv. Neural Inf. Process. Syst., vol. 35, pp. 378–393, 2022

    2022

  58. [58]

    Progressive fusion video super-resolution network via exploiting non-local spatio-temporal correlations,

    P. Yi, Z. Wang, K. Jiang, J. Jiang, and J. Ma, “Progressive fusion video super-resolution network via exploiting non-local spatio-temporal correlations,” inProc. IEEE Int. Conf. Comput. Vis., 2019, pp. 3106–3115

    2019

  59. [59]

    ESIM: an open event camera simulator,

    H. Rebecq, D. Gehrig, and D. Scaramuzza, “ESIM: an open event camera simulator,” inConference on Robot Learning (CORL). PMLR, 2018, pp. 969–982

    2018

  60. [60]

    CED: Color event camera dataset,

    C. Scheerlinck, H. Rebecq, T. Stoffregen, N. Barnes, R. Mahony, and D. Scaramuzza, “CED: Color event camera dataset,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn. Workshop, 2019, pp. 1684–1693

    2019

  61. [61]

    Deep video super-resolution network using dynamic upsampling filters without explicit motion compensation,

    Y . Jo, S. W. Oh, J. Kang, and S. J. Kim, “Deep video super-resolution network using dynamic upsampling filters without explicit motion compensation,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2018, pp. 3224–3232

    2018

  62. [62]

    Deep video super-resolution using HR optical flow estimation,

    L. Wang, Y . Guo, L. Liu, Z. Lin, X. Deng, and W. An, “Deep video super-resolution using HR optical flow estimation,”IEEE Trans. Image Process., vol. 29, pp. 4323–4336, 2020

    2020

  63. [63]

    TDAN: Temporally-deformable alignment network for video super-resolution,

    Y . Tian, Y . Zhang, Y . Fu, and C. Xu, “TDAN: Temporally-deformable alignment network for video super-resolution,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2020, pp. 3360–3369

    2020

  64. [64]

    Recurrent back-projection network for video super-resolution,

    M. Haris, G. Shakhnarovich, and N. Ukita, “Recurrent back-projection network for video super-resolution,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2019, pp. 3897–3906

    2019

  65. [65]

    Real-time, high-speed video decompression using a frame-and event-based DA VIS sensor,

    C. Brandli, L. Muller, and T. Delbruck, “Real-time, high-speed video decompression using a frame-and event-based DA VIS sensor,” inIEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 2014, pp. 686–689

    2014

  66. [66]

    Deep laplacian pyramid networks for fast and accurate super-resolution,

    W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang, “Deep laplacian pyramid networks for fast and accurate super-resolution,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2017, pp. 624–632

    2017

  67. [67]

    Adam: A Method for Stochastic Optimization,

    D. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” inProc. Int. Conf. Learn. Repr., 2015, pp. 1–15

    2015

  68. [68]

    SGDR: stochastic gradient descent with warm restarts,

    I. Loshchilov and F. Hutter, “SGDR: stochastic gradient descent with warm restarts,” inProc. Int. Conf. Learn. Repr., 2017, pp. 1–16

    2017

  69. [69]

    The perception-distortion tradeoff,

    Y . Blau and T. Michaeli, “The perception-distortion tradeoff,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2018, pp. 6228–6237

    2018

  70. [70]

    Learning temporal coherence via self-supervision for gan-based video generation,

    M. Chu, Y . Xie, J. Mayer, L. Leal-Taix ´e, and N. Thuerey, “Learning temporal coherence via self-supervision for gan-based video generation,” ACM Transactions on Graphics (TOG), vol. 39, no. 4, Art. no. 75, 2020

    2020

  71. [71]

    All at once: Temporally adaptive multi-frame interpolation with advanced motion modeling,

    Z. Chi, R. Mohammadi Nasiri, Z. Liu, J. Lu, J. Tang, and K. N. Plataniotis, “All at once: Temporally adaptive multi-frame interpolation with advanced motion modeling,” inProc. Eur. Conf. Comput. Vis., 2020, pp. 107–123

    2020

  72. [72]

    TMP: Temporal Motion Propagation for Online Video Super-Resolution,

    Z. Zhang, R. Li, S. Guo, Y . Cao, and L. Zhang, “TMP: Temporal Motion Propagation for Online Video Super-Resolution,”IEEE Trans. Image Process., 2024

    2024

  73. [73]

    Learning trajectory-aware transformer for video super-resolution,

    C. Liu, H. Yang, J. Fu, and X. Qian, “Learning trajectory-aware transformer for video super-resolution,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2022, pp. 5687–5696

    2022

  74. [74]

    Evenhancer: Empowering effectiveness, efficiency and generalizability for continuous space-time video super-resolution with events,

    S. Wei, F. Li, S. Tang, Y . Zhao, and H. Bai, “Evenhancer: Empowering effectiveness, efficiency and generalizability for continuous space-time video super-resolution with events,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2025, pp. 17 755–17 766

    2025

  75. [75]

    Motion-guided latent diffusion for temporally consistent real-world video super-resolution,

    X. Yang, C. He, J. Ma, and L. Zhang, “Motion-guided latent diffusion for temporally consistent real-world video super-resolution,” inProc. Eur. Conf. Comput. Vis., 2024, pp. 224–242

    2024

  76. [76]

    Seedvr: Seeding infinity in diffusion transformer towards generic video restoration,

    J. Wang, Z. Lin, M. Wei, Y . Zhao, C. Yang, C. C. Loy, and L. Jiang, “Seedvr: Seeding infinity in diffusion transformer towards generic video restoration,” inProc. IEEE Conf. Comput. Vis. Pattern Recogn., 2025, pp. 2161–2172. Dachun Kaireceived the B.S. degree from Hefei University of Technology (HFUT), Hefei, China, in

    2025

  77. [77]

    degree with the University of Science and Technology of China (USTC), Hefei, China

    He is currently pursuing the Ph.D. degree with the University of Science and Technology of China (USTC), Hefei, China. His research interests include computational photography, image and video processing, and deep learning. Jiayao Lureceived the B.S. degree from University of Science and Technology of China (USTC), Hefei, China, in 2018. He is currently p...

    2018