Full search page →

Counting resolution, arithmetic and memory

Optional · supplementary note 3 of 14 for DLCV 09C · Low-Light Image Enhancement. Nothing in the main text depends on it; citation numbers refer to the reference list at the bottom of this page.

Navigate: this page and this track: Navigate: this page and this track

On this page

Supplementary notes · 14

  1. CLAHE: equalizing locally without amplifying noise
  2. More deep LLIE methods
  3. Counting resolution, arithmetic and memory
  4. A bilateral-grid experiment
  5. Implementing and checking trilinear LUTs
  6. Fitting and slicing a bilateral grid in detail
  7. Learnable LUT variants in detail
  8. Structural re-parameterization step by step
  9. Understanding no-reference low-light metrics
  10. Efficient network building blocks
  11. Banding, halos and temporal stability
  12. Bilateral grids and color-table mathematics
  13. From retouching to low light
  14. A lightness-order exercise

Paper guides · 13

  1. KinD: repair reflectance while controlling illumination
  2. Retinex-Net: decompose, adjust and denoise
  3. EnlightenGAN: unpaired appearance learning with content constraints
  4. Zero-DCE and Zero-DCE++: learn curves without reference images
  5. RUAS: search the priors inside an unrolled enhancement model
  6. SCI: train with calibration, deploy one illumination block
  7. Retinexformer: illumination guides restoration
  8. IAT: local affine maps and a global camera-style transform
  9. Multinex: fuse analytic priors into a Retinex residual
  10. CPGA-Net: channel priors, gamma estimation and learned fusion
  11. CPGA-Net+: attention, BDSF and stronger variants
  12. HDRNet: deep bilateral learning for real-time image enhancement
  13. Image-adaptive 3D LUTs (Zeng et al., TPAMI 2022)

Deep Learning for Computer Vision

  1. 02 · Deep Image Classification
View the whole course tree →

Plain version. “Lightweight” is not one number. A model can be small on disk but slow, fast on a GPU but slow on a phone, or cheap in arithmetic but limited by memory. You need to say which cost you mean, at which resolution and on which device.

Precise version. Five costs matter for an enhancement model. The general background (MACs versus FLOPs, why FLOPs are not latency, a latency protocol) is in ML 11; here is what each means for enhancement.

  1. Parameters PP: the number of learned values. They decide the size of the model file and the weight memory. Zero-DCE++ has about 10K parameters [19]; the U-Net-like design counted below has about 1.9 million.
  2. Arithmetic per image, counted in multiply–accumulates. For a convolution layer,
MACs=Hout Wout  k2 Cin Cout,\mathrm{MACs} = H_{\text{out}}\, W_{\text{out}}\; k^2\, C_{\text{in}}\, C_{\text{out}},

where Hout×WoutH_{\text{out}} \times W_{\text{out}} is the size of the output feature map, k×kk \times k the kernel size, and CinC_{\text{in}}, CoutC_{\text{out}} the numbers of input and output channels. One MAC is one multiplication and one addition, so 1 MAC ≈ 2 FLOPs; state which unit you use. 3. MACs per pixel (or per megapixel): the arithmetic divided by the number of input pixels HWHW. This supports arithmetic comparisons across resolutions, because the same model is applied at very different resolutions. A layer that runs at full resolution contributes k2CinCoutk^2 C_{\text{in}} C_{\text{out}} MACs per pixel; a layer that runs on a fixed-size thumbnail contributes almost nothing per pixel at 4K. 4. Memory traffic. Every feature map has to be written to memory and read back by the next layer. A feature map with CC channels at full resolution occupies HWCbH W C b bytes, where bb is the bytes per value (2 for 16-bit floating point, fp16). On phones and embedded chips, moving these bytes often costs more time and energy than the arithmetic. 5. Latency and energy on the target device: the measured time from input frame to output frame, and the energy per frame. These are what users feel, and they can only be measured, not computed.

Designed small, not made small. The models in this chapter are designed to be small: their structure (a curve, an illumination map, a thin network, a table) is chosen so that they are cheap from the start. Making an existing large model smaller after training, by pruning, quantization, knowledge distillation or neural architecture search for a smaller network, is model compression, a related topic covered in DLCV 01C. The two can be combined, but a lightweight enhancer is not necessarily a compressed model.

The code below counts the first four costs for three designs, by pure arithmetic: (1) a seven-layer, 32-channel CNN that runs at full resolution, in the spirit of the DCE-Net of Zero-DCE [18] (the real DCE-Net has skip connections, so its count differs); (2) a U-Net-like restorer [78] with four levels and 32 to 256 channels; and (3) an HDRNet-like design [28] in which a small CNN looks at a fixed 256 × 256 copy of the image and predicts a 16 × 16 × 8 grid of color transforms, followed by a cheap per-pixel step that applies them (explained in the bilateral-grid section).

Code · Python · 33 lines
def conv(cin, cout, k=3, scale=1.0, fixed=None):
    """A k x k convolution on (scale x the input pixels), or on a fixed number of pixels."""
    return dict(params=k * k * cin * cout + cout, macs=k * k * cin * cout, cout=cout, scale=scale, fixed=fixed)

def cost(layers, H, W, per_pixel_apply=0):
    """Parameters, multiply-accumulates (MACs) and the largest feature map (fp16 bytes)."""
    px = [l["fixed"] or H * W * l["scale"] for l in layers]
    macs = sum(l["macs"] * p for l, p in zip(layers, px)) + per_pixel_apply * H * W
    peak = max(2 * l["cout"] * p for l, p in zip(layers, px))
    return sum(l["params"] for l in layers), macs, peak

# (1) a seven-layer, 32-channel CNN at full resolution (in the spirit of DCE-Net)
tiny = [conv(3, 32)] + [conv(32, 32) for _ in range(5)] + [conv(32, 24)]
# (2) a U-Net-like restorer: 4 levels, 32-64-128-256 channels, two convs per level
unet = [conv(3, 32), conv(32, 32), conv(32, 64, scale=1/4), conv(64, 64, scale=1/4),
        conv(64, 128, scale=1/16), conv(128, 128, scale=1/16),
        conv(128, 256, scale=1/64), conv(256, 256, scale=1/64),
        conv(256 + 128, 128, scale=1/16), conv(128, 128, scale=1/16),
        conv(128 + 64, 64, scale=1/4), conv(64, 64, scale=1/4),
        conv(64 + 32, 32), conv(32, 32), conv(32, 3, k=1)]
# (3) HDRNet-like: a CNN on a fixed 256 x 256 copy predicts a 16x16x8 grid of 3x4 affine maps
grid_net = [conv(3, 8, fixed=128**2), conv(8, 16, fixed=64**2), conv(16, 32, fixed=32**2),
            conv(32, 64, fixed=16**2), conv(64, 64, fixed=16**2), conv(64, 64, fixed=16**2),
            conv(64, 96, k=1, fixed=16**2)]
apply = 9 + 48 + 8 * 12 + 12   # guide (3x3 matrix + 16-piece curves), trilinear slice, affine

for H, W, name in [(1080, 1920, "1080p"), (2160, 3840, "4K")]:
    print(f"--- {name}: {H * W / 1e6:.2f} megapixels")
    for label, layers, extra in [("tiny full-res CNN", tiny, 0), ("U-Net-like", unet, 0),
                                 ("low-res grid + slicing", grid_net, apply)]:
        p, m, peak = cost(layers, H, W, extra)
        print(f"{label:23s} params {p:>9,d}  GMACs {m / 1e9:7.1f}  MACs/pixel {m / (H * W):8.0f}"
              f"  largest feature map {peak / 2**20:7.2f} MiB")

Output

--- 1080p: 2.07 megapixels
tiny full-res CNN       params    54,072  GMACs   111.7  MACs/pixel    53856  largest feature map  126.56 MiB
U-Net-like              params 1,946,947  GMACs   336.4  MACs/pixel   162240  largest feature map  126.56 MiB
low-res grid + slicing  params   104,624  GMACs     0.4  MACs/pixel      183  largest feature map    0.25 MiB
--- 4K: 8.29 megapixels
tiny full-res CNN       params    54,072  GMACs   446.7  MACs/pixel    53856  largest feature map  506.25 MiB
U-Net-like              params 1,946,947  GMACs  1345.7  MACs/pixel   162240  largest feature map  506.25 MiB
low-res grid + slicing  params   104,624  GMACs     1.4  MACs/pixel      170  largest feature map    0.25 MiB

Three lessons are in these numbers (all from our own arithmetic, not from any paper):

  • Parameters mislead. The “tiny” CNN has half the parameters of the grid design, yet it needs about 300 times more arithmetic, because every one of its layers runs at full resolution. Parameter count says almost nothing about the cost of a full-resolution network.
  • Resolution multiplies everything at full resolution. Going from 1080p to 4K multiplies the MACs of designs (1) and (2) by exactly 4, the ratio of pixel counts. The grid design grows only through its small per-pixel step.
  • Memory traffic can be the real limit. One 32-channel fp16 feature map at 4K is 3840×2160×32×23840 \times 2160 \times 32 \times 2 bytes, about 506 MiB, and a full-resolution network writes and reads several of them per frame. The grid design’s largest feature map is a quarter of a mebibyte.
Two log-log plots against image size from 0.3 to 33 megapixels, with dashed lines at 1080p and 4K. Left: GMACs per image; the U-Net-like and tiny full-resolution CNN lines rise in parallel from about 50 and 16 GMACs to several thousand, while the low-resolution grid line stays two to three orders of magnitude lower. Right: the largest feature map in MiB; the two full-resolution designs coincide and rise to about 2000 MiB, while the grid design stays flat at 0.25 MiB.
Figure 10 — Cost versus resolution for the three designs of the snippet (our arithmetic). Full-resolution networks scale with the pixel count; a network that runs on a fixed thumbnail does not, and only its cheap per-pixel step grows.

References

  1. Shyandram, “簡介Deep Learning Low-Light Image Enhancement (LLIE)” (Introduction to deep-learning low-light image enhancement, in Chinese), Medium post, 2024; updated 2026. link
  2. A. Foi, M. Trimeche, V. Katkovnik and K. Egiazarian, “Practical Poissonian-Gaussian noise modeling and fitting for single-image raw-data,” IEEE Transactions on Image Processing, vol. 17, no. 10, pp. 1737–1754, 2008. doi
  3. K. He, J. Sun and X. Tang, “Single image haze removal using dark channel prior,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341–2353, 2011. doi
  4. 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, 2017. doi
  5. ITU-R, “Recommendation BT.601-7: Studio encoding parameters of digital television for standard 4:3 and wide-screen 16:9 aspect ratios,” 2011. ITU
  6. Q. Yan, Y. Feng, C. Zhang, et al., “HVI: A new color space for low-light image enhancement,” in Proc. IEEE/CVF CVPR, 2025. arXiv
  7. S. M. Pizer, E. P. Amburn, J. D. Austin, et al., “Adaptive histogram equalization and its variations,” Computer Vision, Graphics, and Image Processing, vol. 39, no. 3, pp. 355–368, 1987. doi
  8. K. Zuiderveld, “Contrast limited adaptive histogram equalization,” in Graphics Gems IV, Academic Press, 1994, pp. 474–485. doi
  9. E. H. Land, “The retinex theory of color vision,” Scientific American, vol. 237, no. 6, pp. 108–128, 1977. doi
  10. D. J. Jobson, Z. Rahman and G. A. Woodell, “Properties and performance of a center/surround retinex,” IEEE Transactions on Image Processing, vol. 6, pp. 451–462, 1997. doi
  11. D. J. Jobson, Z. Rahman and G. A. Woodell, “A multiscale retinex for bridging the gap between color images and the human observation of scenes,” IEEE Transactions on Image Processing, vol. 6, no. 7, pp. 965–976, 1997. doi
  12. X. Dong, Y. Pang and J. Wen, “Fast efficient algorithm for enhancement of low lighting video,” ACM SIGGRAPH 2010 Posters, 2010. SIGGRAPH history doi
  13. 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. doi
  14. 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. doi
  15. C. Li, C. Guo, L. Han, J. Jiang, M.-M. Cheng, J. Gu and C. C. Loy, “Low-light image and video enhancement using deep learning: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 12, pp. 9396–9416, 2022. arXiv
  16. C. Wei, W. Wang, W. Yang and J. Liu, “Deep retinex decomposition for low-light enhancement,” in Proc. British Machine Vision Conference (BMVC), 2018. arXiv project
  17. Y. Jiang, X. Gong, D. Liu, et al., “EnlightenGAN: Deep light enhancement without paired supervision,” IEEE Transactions on Image Processing, vol. 30, pp. 2340–2349, 2021. arXiv
  18. C. Guo, C. Li, J. Guo, et al., “Zero-reference deep curve estimation for low-light image enhancement,” in Proc. IEEE/CVF CVPR, 2020, pp. 1777–1786. arXiv
  19. C. Li, C. Guo and C. C. Loy, “Learning to enhance low-light image via zero-reference deep curve estimation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 8, 2022. arXiv
  20. R. Liu, L. Ma, J. Zhang, X. Fan and Z. Luo, “Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement,” in Proc. IEEE/CVF CVPR, 2021, pp. 10556–10565. arXiv
  21. L. Ma, T. Ma, R. Liu, X. Fan and Z. Luo, “Toward fast, flexible, and robust low-light image enhancement,” in Proc. IEEE/CVF CVPR, 2022, pp. 5627–5636. arXiv
  22. Y. Cai, H. Bian, J. Lin, H. Wang, R. Timofte and Y. Zhang, “Retinexformer: One-stage Retinex-based transformer for low-light image enhancement,” in Proc. IEEE/CVF ICCV, 2023. arXiv code
  23. Y. Wang, R. Wan, W. Yang, H. Li, L.-P. Chau and A. C. Kot, “Low-light image enhancement with normalizing flow,” in Proc. AAAI Conference on Artificial Intelligence, vol. 36, no. 3, pp. 2604–2612, 2022. arXiv
  24. X. Yi, H. Xu, H. Zhang, L. Tang and J. Ma, “Diff-Retinex: Rethinking low-light image enhancement with a generative diffusion model,” in Proc. IEEE/CVF ICCV, 2023. arXiv
  25. J. Hou, Z. Zhu, J. Hou, H. Liu, H. Zeng and H. Yuan, “Global structure-aware diffusion process for low-light image enhancement,” in Advances in Neural Information Processing Systems (NeurIPS), 2023. arXiv
  26. H. Jiang, A. Luo, X. Liu, S. Han and S. Liu, “LightenDiffusion: Unsupervised low-light image enhancement with latent-Retinex diffusion models,” in Proc. European Conference on Computer Vision (ECCV), 2024. arXiv
  27. C. He, C. Fang, Y. Zhang, et al., “Reti-Diff: Illumination degradation image restoration with Retinex-based latent diffusion model,” in Proc. International Conference on Learning Representations (ICLR), 2025. proceedings
  28. M. Gharbi, J. Chen, J. T. Barron, S. W. Hasinoff and F. Durand, “Deep bilateral learning for real-time image enhancement,” ACM Transactions on Graphics (Proc. SIGGRAPH), vol. 36, no. 4, art. 118, 2017. doi arXiv
  29. H. Zeng, J. Cai, L. Li, Z. Cao and L. Zhang, “Learning image-adaptive 3D lookup tables for high performance photo enhancement in real-time,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 4, 2022. doi arXiv
  30. 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. doi
  31. L. Tao, C. Zhu, J. Song, T. Lu, H. Jia and X. Xie, “Low-light image enhancement using CNN and bright channel prior,” in Proc. IEEE International Conference on Image Processing (ICIP), 2017, pp. 3215–3219. doi
  32. S. W. Zamir, A. Arora, S. Khan, et al., “Learning enriched features for real image restoration and enhancement,” in Proc. European Conference on Computer Vision (ECCV), 2020, pp. 492–511. arXiv
  33. X. Xu, R. Wang, C.-W. Fu and J. Jia, “SNR-aware low-light image enhancement,” in Proc. IEEE/CVF CVPR, 2022, pp. 17693–17703. doi
  34. Z. Cui, K. Li, L. Gu, S. Su, P. Gao, Z. Jiang, Y. Qiao and T. Harada, “You only need 90K parameters to adapt light: A light weight transformer for image enhancement and exposure correction,” in Proc. British Machine Vision Conference (BMVC), 2022. paper arXiv
  35. X. Ding, X. Zhang, N. Ma, J. Han, G. Ding and J. Sun, “RepVGG: Making VGG-style ConvNets great again,” in Proc. IEEE/CVF CVPR, 2021, pp. 13728–13737. doi arXiv
  36. Y. Zhang, J. Zhang and X. Guo, “Kindling the darkness: A practical low-light image enhancer,” in Proc. ACM International Conference on Multimedia (ACM MM), 2019, pp. 1632–1640. doi
  37. Y. Zhang, X. Guo, J. Ma, W. Liu and J. Zhang, “Beyond brightening low-light images,” International Journal of Computer Vision, vol. 129, no. 4, pp. 1013–1037, 2021. doi
  38. J. Bai, Y. Yin, Q. He, Y. Li and X. Zhang, “RetinexMamba: Retinex-based Mamba for low-light image enhancement,” arXiv:2405.03349, 2024. arXiv
  39. S.-E. Weng, S.-G. Miaou and R. Christanto, “A lightweight low-light image enhancement network via channel prior and gamma correction,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 39, no. 12, art. 2554013, 2025. doi code manuscript
  40. S.-E. Weng, C.-Y. Hsiao, L.-W. Lu, et al., “Rethinking theoretical illumination for efficient low-light image enhancement” (CPGA-Net+), arXiv:2409.05274, 2024. arXiv
  41. W. Wu, J. Weng, P. Zhang, X. Wang, W. Yang and J. Jiang, “URetinex-Net: Retinex-based deep unfolding network for low-light image enhancement,” in Proc. IEEE/CVF CVPR, 2022, pp. 5891–5900. doi
  42. Z. Liang, C. Li, S. Zhou, R. Feng and C. C. Loy, “Iterative prompt learning for unsupervised backlit image enhancement,” in Proc. IEEE/CVF ICCV, 2023. arXiv
  43. C. Yang, M. Jin, X. Jia, Y. Xu and Y. Chen, “AdaInt: Learning adaptive intervals for 3D lookup tables on real-time image enhancement,” in Proc. IEEE/CVF CVPR, 2022, pp. 17522–17531. CVF arXiv
  44. C. Yang, M. Jin, Y. Xu, R. Zhang, Y. Chen and H. Liu, “SepLUT: Separable image-adaptive lookup tables for real-time image enhancement,” in Proc. European Conference on Computer Vision (ECCV), 2022, pp. 201–217. doi arXiv
  45. T. Wang, Y. Li, J. Peng, Y. Ma, X. Wang, F. Song and Y. Yan, “Real-time image enhancer via learnable spatial-aware 3D lookup tables,” in Proc. IEEE/CVF ICCV, 2021, pp. 2471–2480. CVF arXiv
  46. C. Liu, H. Yang, J. Fu and X. Qian, “4D LUT: Learnable context-aware 4D lookup table for image enhancement,” IEEE Transactions on Image Processing, vol. 32, pp. 4742–4756, 2023. doi arXiv
  47. W. Kim and N. I. Cho, “Image-adaptive 3D lookup tables for real-time image enhancement with bilateral grids,” in Proc. European Conference on Computer Vision (ECCV), 2024, pp. 91–108. doi ECCV
  48. C. Chen, Q. Chen, J. Xu and V. Koltun, “Learning to see in the dark,” in Proc. IEEE/CVF CVPR, 2018, pp. 3291–3300. arXiv
  49. M. V. Conde, G. Geigle and R. Timofte, “InstructIR: High-quality image restoration following human instructions,” in Proc. European Conference on Computer Vision (ECCV), 2024. arXiv
  50. Z. Cui, G.-J. Qi, L. Gu, S. You, Z. Zhang and T. Harada, “Multitask AET with orthogonal tangent regularity for dark object detection,” in Proc. IEEE/CVF ICCV, 2021. arXiv
  51. K. A. Hashmi, G. Kallempudi, D. Stricker and M. Z. Afzal, “FeatEnHancer: Enhancing hierarchical features for object detection and beyond under low-light vision,” in Proc. IEEE/CVF ICCV, 2023. arXiv
  52. M. Dehghani, A. Arnab, L. Beyer, A. Vaswani and Y. Tay, “The efficiency misnomer,” in Proc. International Conference on Learning Representations (ICLR), 2022. ICLR arXiv
  53. A. Ignatov, R. Timofte, S. Liu, et al., “Learned smartphone ISP on mobile GPUs with deep learning, Mobile AI & AIM 2022 challenge: Report,” in Proc. European Conference on Computer Vision (ECCV) Workshops, 2023, pp. 44–70. doi arXiv
  54. 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. doi
  55. R. Zhang, P. Isola, A. A. Efros, E. Shechtman and O. Wang, “The unreasonable effectiveness of deep features as a perceptual metric,” in Proc. IEEE/CVF CVPR, 2018. arXiv
  56. 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. doi
  57. V. Vonikakis, “Datasets” (source of the VV test images), personal web page. link
  58. A. Mittal, R. Soundararajan and A. C. Bovik, “Making a ‘completely blind’ image quality analyzer,” IEEE Signal Processing Letters, vol. 20, no. 3, pp. 209–212, 2013. doi
  59. A. Mittal, A. K. Moorthy and A. C. Bovik, “No-reference image quality assessment in the spatial domain,” IEEE Transactions on Image Processing, vol. 21, no. 12, pp. 4695–4708, 2012. doi
  60. Y. Blau, R. Mechrez, R. Timofte, T. Michaeli and L. Zelnik-Manor, “The 2018 PIRM challenge on perceptual image super-resolution,” in Proc. European Conference on Computer Vision (ECCV) Workshops, 2018. arXiv
  61. C. Ma, C.-Y. Yang, X. Yang and M.-H. Yang, “Learning a no-reference quality metric for single-image super-resolution,” Computer Vision and Image Understanding, vol. 158, pp. 1–16, 2017. doi arXiv
  62. D. Hasler and S. E. Süsstrunk, “Measuring colorfulness in natural images,” in Proc. SPIE 5007, Human Vision and Electronic Imaging VIII, 2003. doi
  63. J. Immerkær, “Fast noise variance estimation,” Computer Vision and Image Understanding, vol. 64, no. 2, pp. 300–302, 1996. doi
  64. J. Liao, S. Hao, R. Hong and M. Wang, “GT-Mean loss: A simple yet effective solution for brightness mismatch in low-light image enhancement,” in Proc. IEEE/CVF ICCV, 2025. arXiv
  65. 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. arXiv
  66. F. Liu and L. Fan, “A review of advancements in low-light image enhancement using deep learning,” Neurocomputing, vol. 652, art. 131052, 2025. arXiv
  67. 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, no. 4, pp. 1153–1184, 2021. doi project
  68. W. Yang, W. Wang, H. Huang, S. Wang and J. Liu, “Sparse gradient regularized deep Retinex network for robust low-light image enhancement,” IEEE Transactions on Image Processing, vol. 30, pp. 2072–2086, 2021. doi
  69. J. Hai, Z. Xuan, R. Yang, et al., “R2RNet: Low-light image enhancement via Real-low to Real-normal Network,” Journal of Visual Communication and Image Representation, vol. 90, art. 103712, 2023. arXiv
  70. R. Wang, X. Xu, C.-W. Fu, et al., “Seeing dynamic scene in the dark: A high-quality video dataset with mechatronic alignment,” in Proc. IEEE/CVF ICCV, 2021, pp. 9680–9689. doi code
  71. V. Bychkovsky, S. Paris, E. Chan and F. Durand, “Learning photographic global tonal adjustment with a database of input/output image pairs,” in Proc. IEEE CVPR, 2011, pp. 97–104. dataset
  72. 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. doi
  73. X. Liu, Z. Wu, A. Li, et al., “NTIRE 2024 challenge on low light image enhancement: Methods and results,” in Proc. IEEE/CVF CVPR Workshops, 2024. arXiv
  74. X. Liu, Z. Wu, F.-A. Vasluianu, et al., “NTIRE 2025 challenge on low light image enhancement: Methods and results,” in Proc. IEEE/CVF CVPR Workshops, 2025. arXiv
  75. S. Zheng, Y. Ma, J. Pan, C. Lu and G. Gupta, “Low-light image and video enhancement: A comprehensive survey and beyond,” arXiv:2212.10772, 2022. arXiv
  76. E. Adhikarla, Y. Liu and B. D. Davison, “Diffusion models for low-light image enhancement: A multi-perspective taxonomy and performance analysis,” arXiv:2510.05976, 2025. arXiv
  77. J. Yan, C. Tu, W. Zhang, Z. Wang, P. Cao, Q. Lin, Y. Fang, X. Liu, Z. Wu, Z. Zhou and R. Timofte, “NTIRE 2026 challenge on efficient low light image enhancement: Methods and results,” NTIRE 2026 workshop report, arXiv:2605.02212, 2026. arXiv
  78. O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proc. Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015, pp. 234–241. doi arXiv
  79. J. Chen, A. Adams, N. Wadhwa and S. W. Hasinoff, “Bilateral guided upsampling,” ACM Transactions on Graphics (Proc. SIGGRAPH Asia), vol. 35, no. 6, 2016. doi project
  80. K. He, J. Sun and X. Tang, “Guided image filtering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397–1409, 2013. doi
  81. C. Chen and J. Mo, “IQA-PyTorch: PyTorch toolbox for image quality assessment,” software (pip package pyiqa). GitHub
  82. J. Ke, Q. Wang, Y. Wang, P. Milanfar and F. Yang, “MUSIQ: Multi-scale image quality transformer,” in Proc. IEEE/CVF ICCV, 2021. arXiv
  83. J. Wang, K. C. K. Chan and C. C. Loy, “Exploring CLIP for assessing the look and feel of images,” in Proc. AAAI Conference on Artificial Intelligence, 2023. arXiv
  84. V. Kannan, S. Malik, N. C. Babu and R. Soundararajan, “Quality assessment of low-light restored images: A subjective study and an unsupervised model,” IEEE Access, vol. 11, pp. 68216–68230, 2023. doi arXiv
  85. ITU-R, “Recommendation BT.500-15: Methodologies for the subjective assessment of the quality of television images,” 2023. ITU
  86. R. A. Bradley and M. E. Terry, “Rank analysis of incomplete block designs: The method of paired comparisons,” Biometrika, vol. 39, no. 3–4, pp. 324–345, 1952. doi
  87. H. Talebi and P. Milanfar, “NIMA: Neural image assessment,” IEEE Transactions on Image Processing, 2018. arXiv
  88. S. Yang, T. Wu, S. Shi, et al., “MANIQA: Multi-dimension attention network for no-reference image quality assessment,” in Proc. IEEE/CVF CVPR Workshops, 2022, pp. 1190–1199. doi arXiv
  89. H. Wu, Z. Zhang, W. Zhang, C. Chen, et al., “Q-Align: Teaching LMMs for visual scoring via discrete text-defined levels,” in Proc. International Conference on Machine Learning (ICML), PMLR 235, 2024. arXiv
  90. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto and H. Adam, “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv:1704.04861, 2017. arXiv
  91. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proc. IEEE/CVF CVPR, 2018, pp. 4510–4520. doi arXiv
  92. W.-S. Lai, J.-B. Huang, O. Wang, E. Shechtman, E. Yumer and M.-H. Yang, “Learning blind video temporal consistency,” in Proc. European Conference on Computer Vision (ECCV), 2018, pp. 179–195. doi arXiv
  93. S. W. Hasinoff, D. Sharlet, R. Geiss, A. Adams, J. T. Barron, F. Kainz, J. Chen and M. Levoy, “Burst photography for high dynamic range and low-light imaging on mobile cameras,” ACM Transactions on Graphics (Proc. SIGGRAPH Asia), vol. 35, no. 6, 2016. doi
  94. J. Chen, S. Paris and F. Durand, “Real-time edge-aware image processing with the bilateral grid,” ACM Transactions on Graphics (Proc. SIGGRAPH), vol. 26, no. 3, art. 103, 2007. doi
  95. C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” in Proc. IEEE International Conference on Computer Vision (ICCV), 1998, pp. 839–846. doi
  96. S. Paris and F. Durand, “A fast approximation of the bilateral filter using a signal processing approach,” International Journal of Computer Vision, vol. 81, no. 1, pp. 24–52, 2009. doi
  97. H. Wu, S. Zheng, J. Zhang and K. Huang, “Fast end-to-end trainable guided filter,” in Proc. IEEE/CVF CVPR, 2018, pp. 1838–1847. doi arXiv
  98. R. Wang, Q. Zhang, C.-W. Fu, X. Shen, W.-S. Zheng and J. Jia, “Underexposed photo enhancement using deep illumination estimation,” in Proc. IEEE/CVF CVPR, 2019, pp. 6842–6850. doi CVF
  99. Y. Lin, Z. Fu, K. Wen, T. Ye, S. Chen, G. Meng, Y. Wang, et al., “DPLUT: Unsupervised low-light image enhancement with lookup tables and diffusion priors,” in Proc. AAAI Conference on Artificial Intelligence, vol. 39, no. 5, pp. 5316–5324, 2025. doi arXiv
  100. K. Dabov, A. Foi, V. Katkovnik and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Transactions on Image Processing, 2007. doi
  101. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” ICLR, 2015. arXiv
  102. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” CVPR, 2009. doi
  103. A. Brateanu, T. Mu, C. O. Ancuti and C. Ancuti, “Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex,” in Proc. IEEE/CVF CVPR, 2026. paper supplement