完整搜尋頁面 →

即插即用先驗與半二次分裂

選讀・DLCV 09・深度影像復原:低階視覺 的補充資料(第 2/11 則)。主線不依賴這則補充;引用編號對應本頁底部的參考文獻。

導覽:本頁與本系列: 導覽:本頁與本系列

本頁內容

補充資料 · 11

  1. 盲超解析度:以模糊核為條件與估計模糊核
  2. 即插即用先驗與半二次分裂
  3. 超解析度的里程碑、主流家族與基準
  4. 傳統與學習式的盲去模糊方法
  5. All-in-one 方法的細節
  6. 人類評分的 IQA 資料集
  7. PIQE 與感知指數
  8. 學習式 NR 評估器如何運作
  9. CLIP-IQA 與 Q-Align 的分數
  10. 擬合 Bradley–Terry 模型
  11. 逐一指標的總覽表

論文導讀 · 13

  1. Restormer:以通道關係取代逐像素注意力
  2. AirNet:先推估退化,再調整修復方式
  3. TransWeather:用學得的天候查詢共用修復模型
  4. PromptIR:依輸入產生特徵 prompt,不需要文字指令
  5. AdaIR:自適應分離頻率,再交換互補資訊
  6. DA-CLIP:把內容引導與退化引導分開
  7. InstructIR:以人類指令引導影像特徵路由
  8. AutoDIR:診斷退化、引導擴散,再修正結構
  9. AgenticIR:規劃、檢查,再修訂修復工具順序
  10. 4KAgent:依忠實度目標選擇修復專家
  11. PromptFix:結合指令、視覺診斷與高頻保留
  12. Deep Image Prior:網路結構即先驗
  13. 綜述論文的詳細介紹

電腦視覺深度學習

  1. 02 · 深度影像分類
  2. 03 · 物件偵測:從 R-CNN 到 DETR
  3. 09 · 深度影像復原:低階視覺
查看完整課程樹 →

白話版。 去模糊方法有兩件工作:讓結果與模糊照片一致,以及讓結果看起來像自然影像。半二次分裂(half-quadratic splitting, HQS)把兩件工作分給各自的步驟,讓兩個步驟輪流進行。「像自然影像」這一步正是去雜訊器做的事,所以你可以直接換上任何去雜訊器,從全變分(total variation, TV)到 CNN 都行,其餘部分完全不用改寫。

精確版。 令 y=Hx+ny = Hx + n 為觀測,其中 HH 是已知退化的矩陣形式(這裡是與模糊核 hh 的卷積;超解析度時還包含降採樣)。「為什麼困難:病態問題」一節的 MAP 問題是

min⁡x  12∥y−Hx∥22+λ Φ(x),\min_x \; \tfrac12\|y - Hx\|_2^2 + \lambda\,\Phi(x),

其中 Φ\Phi 是正則項(負對數先驗),λ>0\lambda > 0 是它的權重。HQS [113] 把 xx 複製成輔助變數 zz,再用二次懲罰項把兩者綁在一起:

min⁡x, z  12∥y−Hx∥22+λ Φ(z)+μ2∥x−z∥22,\min_{x,\,z} \; \tfrac12\|y - Hx\|_2^2 + \lambda\,\Phi(z) + \tfrac{\mu}{2}\|x - z\|_2^2,

其中 μ>0\mu > 0 是懲罰項的權重。對兩個變數輪流最小化,得到

xt+1=(H⊤H+μI)−1(H⊤y+μzt),zt+1=arg⁡min⁡z  12∥z−xt+1∥22+λμ Φ(z),\begin{aligned} x^{t+1} &= (H^\top H + \mu I)^{-1}\bigl(H^\top y + \mu z^{t}\bigr), \\ z^{t+1} &= \arg\min_z \; \tfrac12\|z - x^{t+1}\|_2^2 + \tfrac{\lambda}{\mu}\,\Phi(z), \end{aligned}

其中 tt 是迭代次數,II 是單位矩陣。第一步只牽涉資料。對卷積而言,HH 在傅立葉域是對角的,所以這一步只是逐點相除:x^=(h^‾ y^+μ z^)/(∣h^∣2+μ)\hat x = (\overline{\hat h}\,\hat y + \mu\,\hat z)/(|\hat h|^2 + \mu),帽子代表二維傅立葉轉換,上橫線代表複數共軛。第二步只牽涉先驗,它就是「從受標準差 σt=λ/μ\sigma_t = \sqrt{\lambda/\mu} 的高斯雜訊汙染的 xt+1x^{t+1} 估計乾淨影像」的 MAP 估計 [115]。這就是去雜訊器能當先驗的原因:把 zt+1=Dσt(xt+1)z^{t+1} = \mathcal{D}_{\sigma_t}(x^{t+1}) 寫成任何雜訊強度為 σ\sigma 的高斯去雜訊器 Dσ\mathcal{D}_\sigma,就不必把 Φ\Phi 寫出來。這就是即插即用先驗(plug-and-play priors)[114] 的想法(該文以另一種分裂法 ADMM 提出),而 [115] 把學習出的 CNN 去雜訊器放進 HQS;不同 σ\sigma 的一組去雜訊器扮演 Φ\Phi 的角色。因為 σt=λ/μ\sigma_t = \sqrt{\lambda/\mu},μ\mu 變大就等於去雜訊強度變小:一開始強力平滑,再讓資料項逐漸接手。USRNet [91] 把這個迴圈展開成網路,資料模組就是封閉形式的那一步,先驗模組則是學習出的去雜訊器。Elad 等人的綜述 [68] 討論了去雜訊器作為逆問題基本積木的更廣泛用法。

程式碼。 下面的程式用已知的高斯模糊核把 camera 模糊並加上雜訊,然後比較一步到位的 Tikhonov 濾波器(資料步驟在 z=0z = 0 時的特例)與十次 HQS 迭代,後者換上 scikit-image 的全變分去雜訊器 [116] 或非局部均值(non-local means)去雜訊器 [117]。執行約需兩秒。

程式碼 · Python · 35 行
import numpy as np
from numpy.fft import fft2, ifft2
from skimage import data, img_as_float, transform
from skimage.restoration import denoise_tv_chambolle, denoise_nl_means

rng = np.random.default_rng(0)
x = transform.resize(img_as_float(data.camera()), (256, 256), anti_aliasing=True)
ax = np.arange(15) - 7
h = np.exp(-(ax[:, None] ** 2 + ax[None, :] ** 2) / (2 * 1.5 ** 2)); h /= h.sum()   # known Gaussian blur
P = np.zeros(x.shape); P[:15, :15] = h
H = fft2(np.roll(P, (-7, -7), (0, 1)))                                               # transfer function of h
y = np.real(ifft2(H * fft2(x))) + 0.01 * rng.standard_normal(x.shape)                # y = h * x + n
Y = fft2(y)
psnr = lambda a: 10 * np.log10(1 / np.mean((np.clip(a, 0, 1) - x) ** 2))

def data_step(z, mu):          # x = argmin 1/2||y - h*x||^2 + mu/2||x - z||^2  (closed form in Fourier domain)
    return np.real(ifft2((np.conj(H) * Y + mu * fft2(z)) / (np.abs(H) ** 2 + mu)))

def pnp_hqs(denoise, lam=1e-5, sigmas=np.geomspace(0.05, 0.02, 10)):
    z = y.copy()
    for s in sigmas:                       # denoiser noise level s = sqrt(lam / mu), decreasing
        mu = lam / s ** 2                  # so mu grows from iteration to iteration
        z = denoise(data_step(z, mu), s)   # prior step: any Gaussian denoiser
    return z

tv  = lambda a, s: denoise_tv_chambolle(a, weight=s)
nlm = lambda a, s: denoise_nl_means(a, patch_size=5, patch_distance=6, h=0.8 * s, sigma=s, fast_mode=True)

best = max((psnr(data_step(np.zeros_like(y), mu)), mu) for mu in (1e-3, 3e-3, 1e-2, 3e-2))   # Tikhonov: z = 0
print(f"blurred+noisy {psnr(y):.2f} dB | Tikhonov (best of 4 mu) {best[0]:.2f} dB")
print(f"plug-and-play HQS with TV denoiser  {psnr(pnp_hqs(tv)):.2f} dB")
print(f"plug-and-play HQS with NLM denoiser {psnr(pnp_hqs(nlm)):.2f} dB")
# blurred+noisy 25.79 dB | Tikhonov (best of 4 mu) 28.34 dB
# plug-and-play HQS with TV denoiser  30.17 dB
# plug-and-play HQS with NLM denoiser 30.45 dB

在資料步驟完全不變的情況下,兩種換上的去雜訊器都比一步到位的濾波器高出 1.8 dB 以上。請把它當作示範而不是基準測試:只有一張影像,模糊核是精確已知的,而且 lam 與排程是在這張影像上試過幾組值後選定的(兩種去雜訊器使用相同的值;它們之間 0.28 dB 的差距,相對於改變 lam 的影響很小,見下)。此方法對 lam 很敏感:使用 TV 去雜訊器時,lam=1e-4 得到 28.55 dB,lam=1e-6 得到 25.17 dB。

何時會失敗。 退化 HH 必須已知(模糊核錯了,資料步驟會把錯誤傳下去);去雜訊器只需在排程中的雜訊強度 σt\sigma_t 上運作,所以學習式去雜訊器必須涵蓋這些強度;而對於沒有對應到明確 Φ\Phi 的去雜訊器(例如非局部均值),迴圈一般不保證收斂,因此迭代次數與排程只能直接固定。例如在 [115] 中,去雜訊強度在 30 次迭代內由 49 以指數方式衰減到 1 到 15 之間的某個值(以 0–255 為尺度)。

參考文獻

  1. Shyandram, “Low-Level Vision Task-Image Restoration簡介,” Medium post, 2023; updated 2026. link
  2. Z. Chen, Z. Wu, E. Zamfir, K. Zhang, Y. Zhang, R. Timofte et al., “NTIRE 2024 Challenge on Image Super-Resolution (×4): Methods and Results,” in Proc. IEEE/CVF CVPR Workshops, 2024. arXiv
  3. Z. Chen, K. Liu, J. Gong, J. Wang, L. Sun et al., “NTIRE 2025 Challenge on Image Super-Resolution (×4): Methods and Results,” in Proc. IEEE/CVF CVPR Workshops, 2025. arXiv
  4. X. Wang, L. Xie, C. Dong and Y. Shan, “Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data,” in Proc. IEEE/CVF ICCV Workshops, 2021. arXiv
  5. E. H. Land and J. J. McCann, “Lightness and Retinex Theory,” Journal of the Optical Society of America, vol. 61, no. 1, pp. 1–11, 1971. doi
  6. C. Dong, C. C. Loy, K. He and X. Tang, “Image Super-Resolution Using Deep Convolutional Networks,” IEEE TPAMI, 2016 (conference version ECCV 2014). arXiv
  7. C. Dong, C. C. Loy and X. Tang, “Accelerating the Super-Resolution Convolutional Neural Network,” in Proc. ECCV, 2016. arXiv
  8. W. Shi, J. Caballero, F. Huszár, 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 CVPR, 2016. arXiv
  9. A. Odena, V. Dumoulin and C. Olah, “Deconvolution and Checkerboard Artifacts,” Distill, 2016. link
  10. B. Lim, S. Son, H. Kim, S. Nah and K. M. Lee, “Enhanced Deep Residual Networks for Single Image Super-Resolution,” in Proc. IEEE CVPR Workshops, 2017. arXiv
  11. Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong and Y. Fu, “Image Super-Resolution Using Very Deep Residual Channel Attention Networks,” in Proc. ECCV, 2018. arXiv
  12. C. Ledig, L. Theis, F. Huszár, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang and W. Shi, “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network,” in Proc. IEEE CVPR, 2017. arXiv
  13. X. Wang, K. Yu, S. Wu, J. Gu, Y. Liu, C. Dong, C. C. Loy, Y. Qiao and X. Tang, “ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks,” in Proc. ECCV Workshops, 2018. arXiv
  14. J. Liang, J. Cao, G. Sun, K. Zhang, L. Van Gool and R. Timofte, “SwinIR: Image Restoration Using Swin Transformer,” in Proc. IEEE/CVF ICCV Workshops, 2021. arXiv
  15. X. Chen, X. Wang, J. Zhou, Y. Qiao and C. Dong, “Activating More Pixels in Image Super-Resolution Transformer,” in Proc. IEEE/CVF CVPR, 2023. arXiv
  16. X. Lin, J. He, Z. Chen, Z. Lyu, B. Dai, F. Yu, W. Ouyang, Y. Qiao and C. Dong, “DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior,” arXiv:2308.15070, 2023. arXiv
  17. F. Yu, J. Gu, Z. Li, J. Hu, X. Kong, X. Wang, J. He, Y. Qiao and C. Dong, “Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild,” in Proc. IEEE/CVF CVPR, 2024. arXiv
  18. R. Wu, L. Sun, Z. Ma and L. Zhang, “One-Step Effective Diffusion Network for Real-World Image Super-Resolution,” in Proc. NeurIPS, 2024. arXiv
  19. E. Agustsson and R. Timofte, “NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study,” in Proc. IEEE CVPR Workshops, 2017. doi
  20. K. Zhang, W. Zuo, Y. Chen, D. Meng and L. Zhang, “Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising,” IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142–3155, 2017. arXiv
  21. K. Zhang, W. Zuo and L. Zhang, “FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising,” IEEE Transactions on Image Processing, 2018. arXiv
  22. A. Abdelhamed, S. Lin and M. S. Brown, “A High-Quality Denoising Dataset for Smartphone Cameras,” in Proc. IEEE/CVF CVPR, 2018. doi
  23. S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan and M.-H. Yang, “Restormer: Efficient Transformer for High-Resolution Image Restoration,” in Proc. IEEE/CVF CVPR, 2022. arXiv
  24. L. Chen, X. Chu, X. Zhang and J. Sun, “Simple Baselines for Image Restoration,” in Proc. ECCV, 2022. arXiv
  25. K. He, J. Sun and X. Tang, “Single Image Haze Removal Using Dark Channel Prior,” in Proc. IEEE CVPR, 2009. doi
  26. B. Cai, X. Xu, K. Jia, C. Qing and D. Tao, “DehazeNet: An End-to-End System for Single Image Haze Removal,” IEEE Transactions on Image Processing, 2016. arXiv
  27. B. Li, X. Peng, Z. Wang, J. Xu and D. Feng, “AOD-Net: All-in-One Dehazing Network,” in Proc. IEEE ICCV, 2017. doi · arXiv
  28. X. Liu, Y. Ma, Z. Shi and J. Chen, “GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing,” in Proc. IEEE/CVF ICCV, 2019. arXiv
  29. X. Qin, Z. Wang, Y. Bai, X. Xie and H. Jia, “FFA-Net: Feature Fusion Attention Network for Single Image Dehazing,” in Proc. AAAI, 2020. arXiv
  30. S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang and L. Shao, “Learning Enriched Features for Real Image Restoration and Enhancement,” in Proc. ECCV, 2020. arXiv
  31. Y. Song, Z. He, H. Qian and X. Du, “Vision Transformers for Single Image Dehazing,” IEEE Transactions on Image Processing, vol. 32, 2023. arXiv
  32. B. Li, W. Ren, D. Fu, D. Tao, D. Feng, W. Zeng and Z. Wang, “Benchmarking Single-Image Dehazing and Beyond,” IEEE Transactions on Image Processing, 2019. arXiv
  33. C. O. Ancuti, C. Ancuti, R. Timofte and C. De Vleeschouwer, “O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images,” in Proc. IEEE/CVF CVPR Workshops, 2018. doi
  34. C. O. Ancuti, C. Ancuti, M. Sbert and R. Timofte, “Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images,” in Proc. IEEE ICIP, 2019. doi
  35. A. Geiger, P. Lenz and R. Urtasun, “Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite,” in Proc. IEEE CVPR, 2012. project page
  36. Y.-F. Liu, D.-W. Jaw, S.-C. Huang and J.-N. Hwang, “DesnowNet: Context-Aware Deep Network for Snow Removal,” IEEE Transactions on Image Processing, 2018. arXiv
  37. W.-T. Chen, H.-Y. Fang, J.-J. Ding, C.-C. Tsai and S.-Y. Kuo, “JSTASR: Joint Size and Transparency-Aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect Removal,” in Proc. ECCV, 2020. doi
  38. W. Yang, R. T. Tan, J. Feng, J. Liu, Z. Guo and S. Yan, “Deep Joint Rain Detection and Removal from a Single Image,” in Proc. IEEE CVPR, 2017. arXiv
  39. R. Qian, R. T. Tan, W. Yang, J. Su and J. Liu, “Attentive Generative Adversarial Network for Raindrop Removal from a Single Image,” in Proc. IEEE/CVF CVPR, 2018. arXiv
  40. X. Li, Y. Jin, X. Jin, Z. Wu, B. Li, Y. Wang et al., “NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results,” in Proc. IEEE/CVF CVPR Workshops, 2025. arXiv
  41. C. Wei, W. Wang, W. Yang and J. Liu, “Deep Retinex Decomposition for Low-Light Enhancement,” in Proc. BMVC, 2018. arXiv
  42. 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
  43. H. Zhang, H. Xu, X. Tian, J. Jiang and J. Ma, “Image Fusion Meets Deep Learning: A Survey and Perspective,” Information Fusion, vol. 76, pp. 323–336, 2021. doi
  44. S. Nah, T. H. Kim and K. M. Lee, “Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring,” in Proc. IEEE CVPR, 2017. doi · arXiv
  45. K. He, X. Chen, S. Xie, Y. Li, P. Dollár and R. Girshick, “Masked Autoencoders Are Scalable Vision Learners,” in Proc. IEEE/CVF CVPR, 2022. arXiv
  46. R. Suvorov, E. Logacheva, A. Mashikhin, A. Remizova, A. Ashukha, A. Silvestrov, N. Kong, H. Goka, K. Park and V. Lempitsky, “Resolution-robust Large Mask Inpainting with Fourier Convolutions,” in Proc. IEEE/CVF WACV, 2022. arXiv
  47. S. Sengupta, V. Jayaram, B. Curless, S. Seitz and I. Kemelmacher-Shlizerman, “Background Matting: The World is Your Green Screen,” in Proc. IEEE/CVF CVPR, 2020. arXiv
  48. O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Proc. MICCAI, 2015. arXiv
  49. H. Guo, J. Li, T. Dai, Z. Ouyang, X. Ren and S.-T. Xia, “MambaIR: A Simple Baseline for Image Restoration with State-Space Model,” in Proc. ECCV, 2024. arXiv
  50. H. Guo, Y. Guo, Y. Zha, Y. Zhang, W. Li, T. Dai, S.-T. Xia and Y. Li, “MambaIRv2: Attentive State Space Restoration,” in Proc. IEEE/CVF CVPR, 2025. arXiv
  51. B. Li, X. Liu, P. Hu, Z. Wu, J. Lv and X. Peng, “All-In-One Image Restoration for Unknown Corruption,” in Proc. IEEE/CVF CVPR, 2022. code & paper
  52. J. M. J. Valanarasu, R. Yasarla and V. M. Patel, “TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions,” in Proc. IEEE/CVF CVPR, 2022. arXiv
  53. V. Potlapalli, S. W. Zamir, S. Khan and F. S. Khan, “PromptIR: Prompting for All-in-One Image Restoration,” in Proc. NeurIPS, 2023. arXiv
  54. Y. Cui, S. W. Zamir, S. Khan, A. Knoll, M. Shah and F. S. Khan, “AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation,” in Proc. ICLR, 2025. arXiv
  55. Z. Luo, F. K. Gustafsson, Z. Zhao, J. Sjölund and T. B. Schön, “Controlling Vision-Language Models for Multi-Task Image Restoration,” in Proc. ICLR, 2024. arXiv
  56. M. V. Conde, G. Geigle and R. Timofte, “InstructIR: High-Quality Image Restoration Following Human Instructions,” in Proc. ECCV, 2024. arXiv
  57. H. Zhao, O. Gallo, I. Frosio and J. Kautz, “Loss Functions for Image Restoration with Neural Networks,” IEEE Transactions on Computational Imaging, 2017 (arXiv title: “Loss Functions for Neural Networks for Image Processing”). arXiv
  58. J. Johnson, A. Alahi and L. Fei-Fei, “Perceptual Losses for Real-Time Style Transfer and Super-Resolution,” in Proc. ECCV, 2016. doi · arXiv
  59. L. Jiang, B. Dai, W. Wu and C. C. Loy, “Focal Frequency Loss for Image Reconstruction and Synthesis,” in Proc. IEEE/CVF ICCV, 2021. arXiv
  60. 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
  61. 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
  62. A. Mittal, R. Soundararajan and A. C. Bovik, “Making a ‘Completely Blind’ Image Quality Analyzer,” IEEE Signal Processing Letters, 2013. doi
  63. Y. Blau, R. Mechrez, R. Timofte, T. Michaeli and L. Zelnik-Manor, “The 2018 PIRM Challenge on Perceptual Image Super-resolution,” in Proc. ECCV Workshops, 2018. arXiv
  64. M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler and S. Hochreiter, “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” in Proc. NeurIPS, 2017. arXiv
  65. Y. Blau and T. Michaeli, “The Perception-Distortion Tradeoff,” in Proc. IEEE/CVF CVPR, 2018. arXiv
  66. Z. Wang, J. Chen and S. C. H. Hoi, “Deep Learning for Image Super-Resolution: A Survey,” IEEE TPAMI, 2021. arXiv
  67. C. Tian, L. Fei, W. Zheng, Y. Xu, W. Zuo and C.-W. Lin, “Deep Learning on Image Denoising: An Overview,” Neural Networks, vol. 131, pp. 251–275, 2020. arXiv
  68. M. Elad, B. Kawar and G. Vaksman, “Image Denoising: The Deep Learning Revolution and Beyond — A Survey Paper,” SIAM Journal on Imaging Sciences, vol. 16, no. 3, pp. 1594–1654, 2023. doi · arXiv
  69. K. Zhang, W. Ren, W. Luo, W.-S. Lai, B. Stenger, M.-H. Yang and H. Li, “Deep Image Deblurring: A Survey,” International Journal of Computer Vision, 2022. arXiv
  70. J. Gui, X. Cong, Y. Cao, W. Ren, J. Zhang, J. Zhang, J. Cao and D. Tao, “A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning,” ACM Computing Surveys, 2023. doi · arXiv
  71. W. Yang, R. T. Tan, S. Wang, Y. Fang and J. Liu, “Single Image Deraining: From Model-Based to Data-Driven and Beyond,” IEEE TPAMI, 2021. doi · arXiv
  72. J. Jiang, Z. Zuo, G. Wu, K. Jiang and X. Liu, “A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends,” IEEE TPAMI, 2025. arXiv
  73. X. Li, Y. Ren, X. Jin, C. Lan, X. Wang, W. Zeng, X. Wang and Z. Chen, “Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey,” International Journal of Computer Vision, 2025. arXiv
  74. A. Levin, Y. Weiss, F. Durand and W. T. Freeman, “Understanding and Evaluating Blind Deconvolution Algorithms,” in Proc. IEEE CVPR, 2009, pp. 1964–1971. doi
  75. R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis and W. T. Freeman, “Removing Camera Shake from a Single Photograph,” ACM Transactions on Graphics (Proc. SIGGRAPH), vol. 25, no. 3, pp. 787–794, 2006. doi
  76. Q. Shan, J. Jia and A. Agarwala, “High-quality Motion Deblurring from a Single Image,” ACM Transactions on Graphics (Proc. SIGGRAPH), vol. 27, no. 3, 2008. doi
  77. S. Cho and S. Lee, “Fast Motion Deblurring,” ACM Transactions on Graphics (Proc. SIGGRAPH Asia), vol. 28, no. 5, 2009. doi
  78. L. Xu and J. Jia, “Two-Phase Kernel Estimation for Robust Motion Deblurring,” in Proc. ECCV, 2010, pp. 157–170. doi
  79. D. Krishnan, T. Tay and R. Fergus, “Blind Deconvolution Using a Normalized Sparsity Measure,” in Proc. IEEE CVPR, 2011, pp. 233–240. doi
  80. J. Pan, D. Sun, H. Pfister and M.-H. Yang, “Blind Image Deblurring Using Dark Channel Prior,” in Proc. IEEE CVPR, 2016, pp. 1628–1636. doi
  81. J. Sun, W. Cao, Z. Xu and J. Ponce, “Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal,” in Proc. IEEE CVPR, 2015. arXiv
  82. C. J. Schuler, M. Hirsch, S. Harmeling and B. Schölkopf, “Learning to Deblur,” IEEE TPAMI, vol. 38, no. 7, pp. 1439–1451, 2016. doi · arXiv
  83. A. Chakrabarti, “A Neural Approach to Blind Motion Deblurring,” in Proc. ECCV, 2016. arXiv
  84. D. Ulyanov, A. Vedaldi and V. Lempitsky, “Deep Image Prior,” in Proc. IEEE/CVF CVPR, 2018, pp. 9446–9454. doi · arXiv
  85. D. Ren, K. Zhang, Q. Wang, Q. Hu and W. Zuo, “Neural Blind Deconvolution Using Deep Priors,” in Proc. IEEE/CVF CVPR, 2020. arXiv
  86. O. Kupyn, V. Budzan, M. Mykhailych, D. Mishkin and J. Matas, “DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks,” in Proc. IEEE/CVF CVPR, 2018. arXiv
  87. K. Zhang, W. Zuo and L. Zhang, “Learning a Single Convolutional Super-Resolution Network for Multiple Degradations,” in Proc. IEEE/CVF CVPR, 2018. arXiv
  88. J. Gu, H. Lu, W. Zuo and C. Dong, “Blind Super-Resolution With Iterative Kernel Correction,” in Proc. IEEE/CVF CVPR, 2019. arXiv
  89. S. Bell-Kligler, A. Shocher and M. Irani, “Blind Super-Resolution Kernel Estimation using an Internal-GAN,” in Proc. NeurIPS, 2019. link · arXiv
  90. Z. Luo, Y. Huang, S. Li, L. Wang and T. Tan, “Unfolding the Alternating Optimization for Blind Super Resolution,” in Proc. NeurIPS, 2020. arXiv
  91. K. Zhang, L. Van Gool and R. Timofte, “Deep Unfolding Network for Image Super-Resolution,” in Proc. IEEE/CVF CVPR, 2020. arXiv
  92. K. Zhang, J. Liang, L. Van Gool and R. Timofte, “Designing a Practical Degradation Model for Deep Blind Image Super-Resolution,” in Proc. IEEE/CVF ICCV, 2021. arXiv
  93. A. Liu, Y. Liu, J. Gu, Y. Qiao and C. Dong, “Blind Image Super-Resolution: A Survey and Beyond,” IEEE TPAMI, 2022 (early access). doi · arXiv
  94. 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
  95. 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
  96. N. Venkatanath, D. Praneeth, M. C. Bh, S. S. Channappayya and S. S. Medasani, “Blind Image Quality Evaluation Using Perception Based Features,” in Proc. Twenty First National Conference on Communications (NCC), 2015, pp. 1–6. doi · MATLAB documentation
  97. H. Talebi and P. Milanfar, “NIMA: Neural Image Assessment,” IEEE Transactions on Image Processing, vol. 27, no. 8, pp. 3998–4011, 2018. doi · arXiv
  98. S. Su, Q. Yan, Y. Zhu, C. Zhang, X. Ge, J. Sun and Y. Zhang, “Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network,” in Proc. IEEE/CVF CVPR, 2020, pp. 3664–3673. doi
  99. J. Ke, Q. Wang, Y. Wang, P. Milanfar and F. Yang, “MUSIQ: Multi-scale Image Quality Transformer,” in Proc. IEEE/CVF ICCV, 2021, pp. 5128–5137. doi · arXiv
  100. S. Yang, T. Wu, S. Shi, S. Lao, Y. Gong, M. Cao, J. Wang and Y. Yang, “MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment,” in Proc. IEEE/CVF CVPR Workshops, 2022, pp. 1190–1199. doi · arXiv
  101. C. Chen, J. Mo, J. Hou, H. Wu, L. Liao, W. Sun, Q. Yan and W. Lin, “TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment,” IEEE Transactions on Image Processing, vol. 33, pp. 2404–2418, 2024. doi · arXiv
  102. 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
  103. H. Wu, Z. Zhang, W. Zhang, C. Chen, L. Liao, C. Li, Y. Gao, A. Wang, E. Zhang, W. Sun, Q. Yan, X. Min, G. Zhai and W. Lin, “Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels,” in Proc. ICML, PMLR 235, pp. 54015–54029, 2024. link · arXiv
  104. H. R. Sheikh, M. F. Sabir and A. C. Bovik, “A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms,” IEEE Transactions on Image Processing, vol. 15, no. 11, pp. 3440–3451, 2006 (LIVE Image Quality Assessment Database). doi · database
  105. N. Ponomarenko, L. Jin, O. Ieremeiev, V. Lukin, K. Egiazarian, J. Astola, B. Vozel, K. Chehdi, M. Carli, F. Battisti and C.-C. J. Kuo, “Image Database TID2013: Peculiarities, Results and Perspectives,” Signal Processing: Image Communication, vol. 30, pp. 57–77, 2015. doi · database
  106. H. Lin, V. Hosu and D. Saupe, “KADID-10k: A Large-scale Artificially Distorted IQA Database,” in Proc. Eleventh International Conference on Quality of Multimedia Experience (QoMEX), 2019. doi · database
  107. V. Hosu, H. Lin, T. Sziranyi and D. Saupe, “KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment,” IEEE Transactions on Image Processing, vol. 29, pp. 4041–4056, 2020. arXiv
  108. Y. Fang, H. Zhu, Y. Zeng, K. Ma and Z. Wang, “Perceptual Quality Assessment of Smartphone Photography,” in Proc. IEEE/CVF CVPR, 2020, pp. 3674–3683. doi
  109. J. Gu, H. Cai, H. Chen, X. Ye, J. Ren and C. Dong, “PIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration,” in Proc. ECCV, 2020. arXiv
  110. C. Chen and J. Mo, “IQA-PyTorch: PyTorch Toolbox for Image Quality Assessment,” software (pip package pyiqa), 2022. GitHub
  111. ITU-R, “Recommendation BT.500-15: Methodologies for the Subjective Assessment of the Quality of Television Images,” 2023. ITU
  112. 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
  113. D. Geman and C. Yang, “Nonlinear Image Recovery with Half-Quadratic Regularization,” IEEE Transactions on Image Processing, vol. 4, no. 7, pp. 932–946, 1995. doi
  114. S. V. Venkatakrishnan, C. A. Bouman and B. Wohlberg, “Plug-and-Play Priors for Model Based Reconstruction,” in Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2013, pp. 945–948. doi
  115. K. Zhang, W. Zuo, S. Gu and L. Zhang, “Learning Deep CNN Denoiser Prior for Image Restoration,” in Proc. IEEE/CVF CVPR, 2017, pp. 2808–2817. doi · arXiv
  116. A. Chambolle, “An Algorithm for Total Variation Minimization and Applications,” Journal of Mathematical Imaging and Vision, vol. 20, no. 1–2, pp. 89–97, 2004. doi
  117. A. Buades, B. Coll and J.-M. Morel, “A Non-Local Algorithm for Image Denoising,” in Proc. IEEE CVPR, vol. 2, 2005, pp. 60–65. doi
  118. D. Ulyanov, A. Vedaldi and V. Lempitsky, “Deep Image Prior,” International Journal of Computer Vision, vol. 128, no. 7, pp. 1867–1888, 2020. doi · arXiv
  119. Y. Jiang, Z. Zhang, T. Xue and J. Gu, “AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion,” in Proc. ECCV, 2024. paper
  120. K. Zhu, J. Gu, Z. You, Y. Qiao and C. Dong, “An Intelligent Agentic System for Complex Image Restoration Problems,” in Proc. ICLR, 2025. paper
  121. Y. Zuo, Q. Zheng, M. Wu, X. Jiang, R. Li, J. Wang, Y. Zhang, G. Mai, L. V. Wang, J. Zou, X. Wang, M.-H. Yang and Z. Tu, “4KAgent: Agentic Any Image to 4K Super-Resolution,” in Proc. NeurIPS, 2025. paper
  122. Y. Yu, Z. Zeng, H. Hua, J. Fu and J. Luo, “PromptFix: You Prompt and We Fix the Photo,” in Proc. NeurIPS, 2024. paper