Pith.

Computer Vision and Pattern Recognition · arXiv:2611.16515 v1 · submitted 12 Nov 2026 · 49 references

PiLLVD: A Real-World Low-Light Video Dataset for Dynamic Scenes Captured with Off-the-Shelf Cameras

Yaser Abu Awwad, Paul L. Rosin, Oktay Karakuş

The paper says

“Low-light image and video enhancement has received increasing attention in recent years. However, most existing enhancement methods are developed and evaluated on still images, while progress in low-light video enhancement remains limited by the lack of real-world paired video datasets.”

more of the abstract

Acquiring paired low-light and normal-light video sequences is challenging because it requires spatially and temporally aligned captures while avoiding motion blur, exposure mismatch, and correspondence errors in dynamic scenes. To address this gap, we introduce PiLLVD, the Pi-based Low-Light Video Dataset, a paired low-light video dataset captured using an accessible Raspberry Pi-based multi-camera system with off-the-shelf cameras. PiLLVD provides paired low-light and aligned normal-light reference sequences for dynamic indoor and outdoor scenes, including diverse human and object motion under varying illumination conditions. Unlike existing datasets that are often image-based, static, synthetic, or limited to simple motion patterns, PiLLVD focuses on motion-rich scenes where frame-to-frame stability and motion-related artefacts are important for evaluation. In addition to presenting the dataset and acquisition pipeline, we benchmark representative pre-trained low-light video enhancement methods on PiLLVD under a zero-shot setting. The results show that existing methods do not generalise uniformly across the proposed sequences, highlighting the challenges posed by the proposed dataset and its value for both benchmarking existing methods and supporting the development of future low-light video enhancement algorithms.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

Holds up. PiLLVD provides a needed dynamic paired low-light video dataset with honest evaluation; deserves acceptance. This line is wrong

2 major objections · 7 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 49 references say.

The paper says, at §IV-C Evaluation Protocol

The review did not quote this passage.

Pith says: Objection 1 of 2 · major

The benchmark evaluates only 7 of the 24 sequences (V4, V5, V14, V17 indoor; V2, V5, V7 outdoor). The authors state these were 'selected to cover a broad range of the dataset variation,' but the selection criteria are not formalised.

more of objection 1

Since the dataset is small (24 sequences) and the benchmark is central to the paper's claim, the authors should either justify why these sequences are representative (e.g., by showing that they span the range of illuminance, motion type, and scene structure) or report results on all sequences. At minimum, explain what metric was used to ensure coverage.

The paper says, at §III-A4 Alignment accuracy

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.64):

“Very fast motion also introduces physical motion blur, making it difficult to establish accurate matches between the paired low-light and normal-light frames.”

Pith says: Objection 2 of 2 · major

Table III reports mean matched feature displacement reduced from 18.79 to 0.56 px, which is excellent on average. However, the authors acknowledge (Section V) that perfect alignment remains difficult around fast-moving objects and low-texture areas. The paper should provide per-video or per-frame alignment statistics (e.g., standard deviation, worst-case displacement) to quantify the variation. Without this, the reader cannot assess how residual misalignment might affect metric scores in challenging frames.

7 minor objections

The paper says, at §I Introduction

Pith says: minor objection 1 of 7

The contributions list states 'post-capture alignment and evaluation pipeline to improve spatial correspondence.' The evaluation in Table III is clear, but the paper would benefit from a brief description of which specific features (e.g., SIFT, ORB) were used for the feature-based metrics.

The paper says, at §III-A1 Hardware

Pith says: minor objection 2 of 7

The beam splitter is listed as 70/30 (R/T). Clarify which camera (low-light or normal-light) receives the transmitted vs. reflected path. From the system description it appears the low-light camera gets 30% transmission, but this should be stated explicitly.

show 5 more

The paper says, at Table I

Pith says: minor objection 3 of 7

The 'Motion diversity' column for existing datasets is marked 'Unknown' or 'Low'. While plausible, this is a qualitative assessment. Consider providing a quantitative measure (e.g., average optical flow magnitude or variance) to support the claim that PiLLVD has higher motion diversity.

The paper says, at §IV-D Evaluation Metrics

Pith says: minor objection 4 of 7

The mTWE metric is adapted from [48] by replacing FlowNet2 with RAFT. The authors should state whether this change was validated against the original metric (e.g., on a subset) or note any potential differences in the temporal consistency scores.

The paper says, at Figure 6 & 7

Pith says: minor objection 5 of 7

The qualitative figures are printed at small scale. In the final version, consider providing zoomed-in crops of the most informative regions (e.g., the moving person in the outdoor sequence) to make visual differences more discernible.

The paper says, at §V Discussion & Limitations

Pith says: minor objection 6 of 7

The sentence 'very fast motion also introduces physical motion blur' is accurate, but the paper does not report motion-blur statistics across the dataset. A simple categorisation (e.g., number of frames with estimated blur > threshold) would help users understand the dataset's difficulty.

The paper says, at General

Pith says: minor objection 7 of 7

The reference list includes several entries marked as 'arXiv preprint' or 'to appear'. Some of these (e.g., [29] from 2025) should be checked for final publication venues in the camera-ready version.

What would settle it

Select 200 frames with highest estimated alignment error (e.g., top 10% by feature displacement) across diverse sequences. Manually verify and, if needed, correct alignment via supervised homography refinement. Recompute PSNR, SSIM, LPIPS, and mTWE on this cleaned subset. If the relative ranking of methods (especially the best overall performer) does not change compared to the original evaluation, the alignment concern is not load-bearing. If rankings change, the evaluation protocol must be revised, but this is unlikely given the large inter-method variance.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 13 Nov 2026

  1. Reader holds up confidence high
  2. Skeptic agrees 27 s · 18,731 tokens read, 2,583 written
  3. Editor wrote the verdict above 24 s · 19,525 tokens read, 1,168 written
  4. Referee minor revision: 2 major objections, 7 minor 37 s · 19,040 tokens read, 1,752 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

This is a straightforward dataset paper that does what it says. The acquisition system is cheap and reproducible, the alignment pipeline is clearly described, and the benchmark results are presented without overclaim. The central claim—that existing LLVE methods generalise poorly to uncontrolled dynamic scenes—is supported by the data.

The authors are transparent about limitations: alignment imperfections, small size, indoor bias. They quantify alignment quality with feature-based metrics (Table III) rather than glossing over it. That is good practice.

Soft spots: The dataset is small (24 sequences, 4531 frames), and the ground truth is warped normal-light frames, not perfectly aligned. The authors acknowledge this and argue that residual errors are small relative to the performance gaps observed. I find that argument convincing for the benchmark's main conclusion, but users should be aware when using PiLLVD for fine-tuning or pixel-level supervision. The outdoor coverage is thin—only 3 sequences—but the paper states plans to expand.

One minor concern: the benchmark only includes 5 methods, all of which are reasonably known. It would be stronger to include a wider set, but given the paper's scope (dataset introduction rather than method comparison), this is acceptable.

This paper is for the low-light video community. It will be cited because it fills a specific gap (real dynamic paired data, publicly available). It deserves a serious referee and should be accepted after minor revisions (perhaps suggesting additional outdoor sequences or a note about ground truth limitations for fine-tuning).

The strongest objection

The paper's central claim—that PiLLVD provides a valuable benchmark exposing generalization failures of existing low-light video enhancement models—is well-supported. The weakest link is the reliance on warped normal-light frames as ground truth for reference-based evaluation, as the reader noted. The authors acknowledge this limitation (Section V: 'perfect pixel-level alignment remains difficult in challenging frames') and provide quantitative alignment metrics (Table III: mean displacement 0.56 px, inlier ratio 0.931). These metrics suggest that residual misalignment is small on average, but the impact on evaluation—especially around fast motion and low-texture regions—could affect metric accuracy. However, the benchmark results (Tables IV and V) show large performance gaps between methods (e.g., PSNR differences of 5–10 dB), so small alignment errors are unlikely to reverse the overall conclusion that no single method generalizes uniformly. The authors' transparency and the robustness of the observed differences make this a non-fatal concern. No evidence of circularity, inconsistency, or overclaiming was found.

The stress-test confirms the reader's assessment. The paper's strongest claim—that the dataset challenges existing models—is supported by quantitative and qualitative evidence. The weakest assumption, alignment quality, is explicitly acknowledged and backed by reasonable metrics. The concrete test would further validate robustness, but the reader's verdict (ACCEPT) remains appropriate given the current evidence and transparency. No load-bearing flaw was identified; the dataset and benchmark serve their stated purpose.

The referee's report

If the dataset is used by the community, PiLLVD addresses a clear gap: the lack of publicly available, real-world paired low-light video data with dynamic scenes. Existing datasets are often static, synthetic, or not publicly released. The benchmark demonstrates that current pre-trained methods fail to generalise, confirming the need for more robust video-level enhancement approaches. The low-cost, reproducible capture system also lowers the barrier for future data collection. The release of aligned reference frames and a transparent evaluation protocol strengthens the contribution.

Pith's reading of the paper (a machine's summary, not the authors')

The paper introduces PiLLVD, a real-world paired low-light video dataset captured with a low-cost Raspberry Pi-based dual-camera system and a beam splitter. Unlike existing datasets that are static, synthetic, or constrained by controlled motion, PiLLVD focuses on dynamic indoor and outdoor scenes with diverse uncontrolled human and object motion under varying illumination. The authors benchmark five pre-trained low-light video enhancement models in a zero-shot setting, showing that no model consistently outperforms others across PSNR, SSIM, LPIPS, and temporal consistency (mTWE). Some models improve brightness but introduce colour shifts or ghosting; others preserve temporal stability but under-enhance the image. The dataset exposes that existing methods do not generalise uniformly to real-world dynamic low-light conditions, making PiLLVD a challenging benchmark for developing more robust, temporally consistent low-light video enhancement algorithms.

What carries the argument. The PiLLVD dataset itself is the central object: a collection of spatially and temporally aligned low-light and normal-light video pairs captured by a synchronised dual-camera system using a 70/30 beam splitter. The acquisition hardware (three Raspberry Pis, two Arducam IMX519 cameras) is low-cost and reproducible. The post-capture alignment pipeline uses histogram matching on the low-light frames, TV-L1 optical flow between the enhanced low-light and normal-light frames, and warps the normal-light frames to the low-light viewpoint, avoiding interpolation on the input. The zero-shot benchmark protocol evaluates five pre-trained models on the same sequences with full-reference (PSNR, SSIM, LPIPS) and temporal (masked temporal warping error, mTWE) metrics, exposing trade-offs between fidelity, perceptual quality, and stability.

Core claim. The paper's central contribution is PiLLVD, a paired low-light and normal-light video dataset of 24 sequences (4,531 frames) featuring uncontrolled human and object motion, spanning 77–401 lux. The acquisition system uses a Raspberry Pi master–slave architecture with beam-splitter optics to synchronise two identical cameras with sub-millisecond temporal offset. A post-capture alignment pipeline reduces mean matched feature displacement from 18.79 px to 0.56 px. Benchmarking on four indoor and three outdoor sequences shows that LLVE-STCD leads in indoor SSIM and LPIPS, while DP3DF yields the best temporal consistency (lowest mTWE), and SDSDNet or StableLLVE lead on outdoor LPIPS in different sequences. No method dominates across all metrics and scenes, confirming that dynamic real-world low-light video remains an open challenge.

The premise it rests on. The aligned normal-light frames serve as reliable ground truth despite residual misalignment from the optical-flow-based warping pipeline, which the authors acknowledge becomes difficult around fast motion, motion blur, and low-texture regions.

If the paper is right (Pith's inferences, not the authors')

Researchers can use PiLLVD as a standard benchmark to evaluate temporal stability and motion-aware enhancement of low-light video models.

The dataset's diverse motion patterns (walking, hand movements, object manipulation) enable analysis of how enhancement methods handle non-rigid deformation and occlusion.

The zero-shot results provide baselines for future supervised or fine-tuned models trained on PiLLVD, which may achieve better generalisation than models trained on static or synthetic data.

The low-cost camera rig design can be replicated and extended by other groups, supporting community-driven collection of additional dynamic paired videos.

The observed failure modes (colour shift, ghosting, over-enhancement) suggest that current models lack joint optimization for motion compensation and illumination correction; future work may need to integrate optical-flow or transformer-based temporal modules within the enhancement head.

Because PiLLVD focuses on static-camera dynamic scenes, it does not test camera motion; a natural extension would be to record handheld or moving platform sequences, which would stress alignment and temporal consistency further.

The alignment pipeline's reliance on histogram matching and optical flow could be replaced by a learned alignment model trained on synthetic paired data, potentially reducing residual misalignment in low-texture regions.

The limited number of sequences (24) and frame count (4,531) means that dataset size may restrict statistical power; future work should verify whether the observed model rankings hold on an expanded version with more outdoor scenes and faster motion.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Low-light image and video enhancement has received increasing attention in recent years. However, most existing enhancement methods are developed and evaluated on still images, while progress in low-light video enhancement remains limited by the lack of real-world paired video datasets. Acquiring paired low-light and normal-light video sequences is challenging because it requires spatially and temporally aligned captures while avoiding motion blur, exposure mismatch, and correspondence errors in dynamic scenes. To address this gap, we introduce PiLLVD, the Pi-based Low-Light Video Dataset, a paired low-light video dataset captured using an accessible Raspberry Pi-based multi-camera system with off-the-shelf cameras. PiLLVD provides paired low-light and aligned normal-light reference sequences for dynamic indoor and outdoor scenes, including diverse human and object motion under varying illumination conditions. Unlike existing datasets that are often image-based, static, synthetic, or limited to simple motion patterns, PiLLVD focuses on motion-rich scenes where frame-to-frame stability and motion-related artefacts are important for evaluation. In addition to presenting the dataset and acquisition pipeline, we benchmark representative pre-trained low-light video enhancement methods on PiLLVD under a zero-shot setting. The results show that existing methods do not generalise uniformly across the proposed sequences, highlighting the challenges posed by the proposed dataset and its value for both benchmarking existing methods and supporting the development of future low-light video enhancement algorithms.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-11-13

The authors' main claim, as the classifier picked it out 1.00

“The results show that existing methods do not generalise uniformly across the proposed sequences, highlighting the challenges posed by the proposed dataset and its value for both benchmarking existing methods and supporting the development of future low-light video enhancement algorithms.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.12 · states limitation 0.35 · human participants 0.23 · controlled comparison 0.46 · randomized assignment 0.01 · states quantitative result 0.05 · compares with prior results 0.84 · mentions code or data availability 0.19

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Low-light image and video enhancement has received increasing attention in recent years. background 1.00 0.03 0.02 asserted 1.00
However, most existing enhancement methods are developed and evaluated on still images, while progress in low-light video enhancement remains limited by the lack of real-world paired video datasets. gap 0.95 0.06 0.03 asserted 1.00
Acquiring paired low-light and normal-light video sequences is challenging because it requires spatially and temporally aligned captures while avoiding motion blur, exposure mismatch, and correspondence errors in dynamic scenes. gap 0.58 0.08 0.02 asserted 1.00
To address this gap, we introduce PiLLVD, the Pi-based Low-Light Video Dataset, a paired low-light video dataset captured using an accessible Raspberry Pi-based multi-camera system with off-the-shelf cameras. contribution 0.99 0.94 0.06 asserted 1.00
PiLLVD provides paired low-light and aligned normal-light reference sequences for dynamic indoor and outdoor scenes, including diverse human and object motion under varying illumination conditions. contribution 0.95 0.85 0.05 asserted 1.00
Unlike existing datasets that are often image-based, static, synthetic, or limited to simple motion patterns, PiLLVD focuses on motion-rich scenes where frame-to-frame stability and motion-related artefacts are important for evaluation. contribution 0.96 0.44 0.05 asserted 1.00
In addition to presenting the dataset and acquisition pipeline, we benchmark representative pre-trained low-light video enhancement methods on PiLLVD under a zero-shot setting. method 0.52 0.95 0.05 asserted 0.95
The results show that existing methods do not generalise uniformly across the proposed sequences, highlighting the challenges posed by the proposed dataset and its value for both benchmarking existing methods and supporting the development of future low-light video enhancement algorithms. interpretation 0.52 0.95 0.83 asserted 1.00

What kind of paper the classifier reports this is: dataset or benchmark 1.00 · evidence from observation or experiment 1.00

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 6,379 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (7)
Figure 1 of the paper
Figure 1. (a), (b) Sample frames from existing paired low-light video datasets; (c) sample frames from our dataset, shown from left to right as (f
Figure 2 of the paper
Figure 2. The proposed camera setup for capturing paired low-light and normal-light video frames. (a) Schematic diagram showing the optical path and
Figure 3 of the paper
Figure 3. Overview of the proposed acquisition and post-processing pipeline for constructing paired low-light and normal-light data.
Figure 4 of the paper
Figure 4. Comparison of normal-light and low-light frame fusion results before
Figure 5 of the paper
Figure 5. Distribution of measured illuminance values for the low-light videos in the dataset.
Figure 6 of the paper
Figure 6. Qualitative comparison on three consecutive frames from a representative indoor PiLLVD sequence. The comparison includes the low-light input,
Figure 7 of the paper
Figure 7. Qualitative comparison on three consecutive frames from a representative outdoor PiLLVD sequence. The comparison includes the low-light input,

Figures are the authors', reproduced from the paper.

References (49)
  1. [1] Y . Abu Awwad, P. Rosin, and O. Karakus ¸, “PiLLVD: Real-world low-light video dataset for dynamic scenes,” 2026, dataset. [Online]. Available: https://doi.org/10.5281/zenodo.23015904 on Pithdoi:10.5281/zenodo.23015904
  2. [2] Y . Abu Awwad, O. Rana, and C. Perera, “Anomaly detection on the edge using smart cameras under low-light conditions,”Sensors, vol. 24, no. 3, p. 772, 2024 on Pith
  3. [3] C. Chen, Q. Chen, J. Xu, and V . Koltun, “Learning to see in the dark,” inProceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3291–3300 on Pith
  4. [4] S. Anwar, C. Li, and F. Porikli, “Deep underwater image enhancement,” arXiv preprint arXiv:1807.03528, 2018 on PithPith's reviewarXiv
  5. [5] N. L. Allison and S. Destefano, “Equipment and techniques for nocturnal wildlife studies,”Wildlife Society Bulletin, vol. 34, no. 4, pp. 1036–1044, 2006 on Pith
  6. [6] K. Zuiderveld, “Contrast limited adaptive histogram equalization,” in Graphics Gems IV. Academic Press Professional, Inc., 1994, pp. 474– 485 on Pith
  7. [7] E. H. Land, “The Retinex theory of color vision,”Journal of the Optical Society of America, vol. 61, no. 1, pp. 1–11, 1977 on Pith
  8. [8] C. Li, J. Guo, F. Porikli, and Y . Pang, “LightenNet: A convolutional neural network for weakly illuminated image enhancement,”Pattern recognition letters, vol. 104, pp. 15–22, 2018 on Pith
  9. [9] C. Guo, C. Li, J. Guo, C. C. Loy, J. Hou, S. Kwong, and R. Cong, “Zero- reference deep curve estimation for low-light image enhancement,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 1780–1789 on Pith
  10. [10] C. Wei, W. Wang, W. Yang, and J. Liu, “Deep retinex decomposition for low-light enhancement,”arXiv preprint arXiv:1808.04560, 2018 on PithPith's reviewarXiv
  11. [11] J. Cai, S. Gu, and L. Zhang, “Learning a deep single image contrast enhancer from multi-exposure images,”IEEE Transactions on Image Processing, vol. 27, no. 4, pp. 2049–2062, 2018 on Pith
  12. [12] F. Zhang, Y . Li, S. You, and Y . Fu, “Learning temporal consistency for low light video enhancement from single images,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021, pp. 4967–4976 on Pith
  13. [13] B. Peng, X. Zhang, J. Lei, Z. Zhang, N. Ling, and Q. Huang, “Lve- s2d: Low-light video enhancement from static to dynamic,”IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 12, pp. 8342–8352, 2022 on Pith
  14. [14] L.-W. Wang, W.-C. Siu, Z.-S. Liu, C.-T. Li, and D. P.-K. Lun, “Video lightening with dedicated cnn architecture,” in2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 2021, pp. 6447– 6454 on Pith
  15. [15] S. Chhirolya, S. Malik, and R. Soundararajan, “Low light video enhance- ment by learning on static videos with cross-frame attention,”arXiv preprint arXiv:2210.04290, 2022 on PithPith's reviewarXiv
  16. [16] L. Liu, J. An, J. Liu, S. Yuan, X. Chen, W. Zhou, H. Li, Y . F. Wang, and Q. Tian, “Low-light video enhancement with synthetic event guidance,” inProceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications... on Pith
  17. [17] H. Jiang and Y . Zheng, “Learning to see moving objects in the dark,” inProceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 7324–7333 on Pith
  18. [18] C. Chen, Q. Chen, M. N. Do, and V . Koltun, “Seeing motion in the dark,” inProceedings of the IEEE/CVF International conference on computer vision, 2019, pp. 3185–3194 on Pith
  19. [19] R. Wang, X. Xu, C.-W. Fu, J. Lu, B. Yu, and J. Jia, “Seeing dynamic scene in the dark: A high-quality video dataset with mechatronic alignment,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 9700–9709 on Pith
  20. [20] K. Ma, K. Zeng, and Z. Wang, “Perceptual quality assessment for multi-exposure image fusion,”IEEE Transactions on Image Processing, vol. 24, no. 11, pp. 3345–3356, 2015. 14 on Pith
show 29 more
  1. [21] S. Wang, J. Zheng, H.-M. Hu, and B. Li, “Naturalness preserved enhancement algorithm for non-uniform illumination images,”IEEE transactions on image processing, vol. 22, no. 9, pp. 3538–3548, 2013 on Pith
  2. [22] X. Guo, Y . Li, and H. Ling, “Lime: Low-light image enhancement via illumination map estimation,”IEEE Transactions on image processing, vol. 26, no. 2, pp. 982–993, 2016 on Pith
  3. [23] C. Lee, C. Lee, and C.-S. Kim, “Contrast enhancement based on layered difference representation of 2d histograms,”IEEE transactions on image processing, vol. 22, no. 12, pp. 5372–5384, 2013 on Pith
  4. [24] D.-T. Dang-Nguyen, C. Pasquini, V . Conotter, and G. Boato, “Raise: A raw images dataset for digital image forensics,” inProceedings of the 6th ACM multimedia systems conference, 2015, pp. 219–224 on Pith
  5. [25] R. Wang, Q. Zhang, C.-W. Fu, X. Shen, W.-S. Zheng, and J. Jia, “Underexposed photo enhancement using deep illumination estimation,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 6849–6857 on Pith
  6. [26] J. Liu, D. Xu, W. Yang, M. Fan, and H. Huang, “Benchmarking low-light image enhancement and beyond,”International Journal of Computer Vision, vol. 129, pp. 1153–1184, 2021 on Pith
  7. [27] Y . P. Loh and C. S. Chan, “Getting to know low-light images with the exclusively dark dataset,”Computer Vision and Image Understanding, vol. 178, pp. 30–42, 2019 on Pith
  8. [28] D. Triantafyllidou, S. Moran, S. McDonagh, S. Parisot, and G. Slabaugh, “Low light video enhancement using synthetic data produced with an intermediate domain mapping,” inEuropean conference on computer vision. Springer, 2020, pp. 103–119 on Pith
  9. [29] J. Wang, H. Fu, W. Zheng, X. Wang, X. Wang, H. Zhang, and H. Ma, “Rethinking the low-light video enhancement: Benchmark datasets and methods,”IEEE Transactions on Image Processing, pp. 1–1, 2025 on Pith
  10. [30] R. Lin, N. Anantrasirichai, G. Huang, J. Lin, Q. Sun, A. Malyugina, and D. R. Bull, “Bvi-rlv: A fully registered dataset and benchmarks for low-light video enhancement,”arXiv preprint arXiv:2407.03535, 2024 on PithPith's reviewarXiv
  11. [31] K. G. Lore, A. Akintayo, and S. Sarkar, “LLNet: A deep autoencoder approach to natural low-light image enhancement,”Pattern Recognition, vol. 61, pp. 650–662, 2017 on Pith
  12. [32] F. Lv, F. Lu, J. Wu, and C. Lim, “MBLLEN: Low-light image/video enhancement using cnns.” inBMVC, vol. 220, no. 1. Northumbria University, 2018, p. 4 on Pith
  13. [33] Y . Zhang, X. Guo, J. Ma, W. Liu, and J. Zhang, “Beyond brightening low-light images,”International Journal of Computer Vision, vol. 129, pp. 1013–1037, 2021 on Pith
  14. [34] Y . Jiang, X. Gong, D. Liu, Y . Cheng, C. Fang, X. Shen, J. Yang, P. Zhou, and Z. Wang, “EnlightenGAN: Deep light enhancement without paired supervision,”IEEE Transactions on Image Processing, vol. 30, pp. 2340–2349, 2021 on Pith
  15. [35] W. Yang, S. Wang, Y . Fang, Y . Wang, and J. Liu, “From fidelity to perceptual quality: A semi-supervised approach for low-light image en- hancement,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3063–3072 on Pith
  16. [36] S. Zheng and G. Gupta, “Semantic-guided zero-shot learning for low- light image/video enhancement,” inProceedings of the IEEE/CVF Winter conference on applications of computer vision, 2022, pp. 581– 590 on Pith
  17. [37] S. Zhou, C. Li, and C. C. Loy, “Lednet: Joint low-light enhancement and deblurring in the dark,” inProceedings of the European Conference on Computer Vision, 2022 on Pith
  18. [38] Y . Hui, Y . Liu, Y . Liu, F. Jia, J. Pan, R. Chan, and T. Zeng, “VJT: A video transformer on joint tasks of deblurring, low-light enhancement and denoising,”arXiv preprint arXiv:2401.14754, 2024 on PithPith's reviewarXiv
  19. [39] S. Van der Walt, J. L. Sch ¨onberger, J. Nunez-Iglesias, F. Boulogne, J. D. Warner, N. Yager, E. Gouillart, and T. Yu, “scikit-image: image processing in python,”PeerJ, vol. 2, p. e453, 2014 on Pith
  20. [40] J. S ´anchez P´erez, E. Meinhardt-Llopis, and G. Facciolo, “TV-L1 Optical Flow Estimation,”Image Processing On Line, vol. 3, pp. 137–150, 2013, https://doi.org/10.5201/ipol.2013.26 on Pithdoi:10.5201/ipol.2013.26
  21. [41] B. Zitov ´a and J. Flusser, “Image registration methods: a survey,”Image and Vision Computing, vol. 21, no. 11, pp. 977–1000, 2003 on Pith
  22. [42] R. Hartley and A. Zisserman,Multiple View Geometry in Computer Vision, 2nd ed. Cambridge University Press, 2004 on Pith
  23. [43] M. A. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,”Communications of the ACM, vol. 24, no. 6, pp. 381–395, 1981 on Pith
  24. [44] X. Xu, R. Wang, C.-W. Fu, and J. Jia, “Deep parametric 3d filters for joint video denoising and illumination enhancement in video super resolution,” inAAAI, 2023 on Pith
  25. [45] X. Xu, K. Zhou, T. Hu, J. Wu, R. Wang, H. Peng, and B. Yu, “Low- light video enhancement via spatial-temporal consistent decomposition,” inIJCAI, 2025 on Pith
  26. [46] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,”IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004 on Pith
  27. [47] R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The unreasonable effectiveness of deep features as a perceptual metric,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 586–595 on Pith
  28. [48] W.-S. Lai, J.-B. Huang, O. Wang, E. Shechtman, E. Yumer, and M.- H. Yang, “Learning blind video temporal consistency,” inEuropean Conference on Computer Vision, 2018 on Pith
  29. [49] Z. Teed and J. Deng, “RAFT: Recurrent all-pairs field transforms for optical flow,” inEuropean Conference on Computer Vision, 2020 on Pith

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment