完整搜尋頁面 →

KernelGAN:以單圖 GAN 估計核(NeurIPS 2019)

選讀・DLCV 09A.1・盲與真實世界影像超解析度 的論文導讀(第 3/11 篇)。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 · 3

  1. 逐步看高階退化管線
  2. Sinc 濾波與振鈴
  3. 為什麼核難以識別

論文導讀 · 11

  1. SRMD:一個網路處理多種已知退化(CVPR 2018)
  2. IKC:反覆修正模糊核(CVPR 2019)
  3. KernelGAN:以單圖 GAN 估計核(NeurIPS 2019)
  4. DAN:展開交替最佳化(NeurIPS 2020)
  5. DASR:對比退化表示(CVPR 2021)
  6. BSRGAN:實用的退化模型(ICCV 2021)
  7. Real-ESRGAN:純合成高階退化(ICCVW 2021)
  8. StableSR:以時間感知編碼器控制凍結先驗(IJCV 2024)
  9. DiffBIR:先移除退化,再生成細節(ECCV 2024)
  10. SeeSR:退化感知的語意提示(CVPR 2024)
  11. SUPIR:擴大先驗、資料與文字控制(CVPR 2024)

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 →

挑戰

核隨鏡頭與手震變,非盲 SR 需要逐圖估計。早期跨尺度區塊搜尋 [11] 高於 ×2 困難且約 45 分鐘。KernelGAN [12] 只用測試圖本身做無外部資料核估計。

方法

降取樣生成器與區塊鑑別器從單張輸入的內部統計學習,再由另一個超解析度流程使用估得的降取樣核。
原論文圖 2 — 降取樣生成器與區塊鑑別器從單張輸入的內部統計學習,再由另一個超解析度流程使用估得的降取樣核。

圖片來源: [12], Published paper PDF, PDF 第 4 頁. 原始 PDF.

原理。 學一個縮圖器,使其小區塊分布與原 LR 難分辨;利用 GAN 做跨尺度分布匹配。

目標。 u,vu,v 是 LR 裁切,GG 為縮圖器,DD 為區塊判別器,官方交替最小化:

LD=12E[∣D(u)−1∣+∣D(G(v))∣],LG=E∣D(G(v))−1∣+R(k).\mathcal L_D=\tfrac12\mathbb E\bigl[\lvert D(u)-1\rvert+\lvert D(G(v))\rvert\bigr],\qquad \mathcal L_G=\mathbb E\lvert D(G(v))-1\rvert+R(k).

絕對誤差對判別空間圖平均,R(k)R(k) 正規化有效核。判別器真標 1、生成標 0,生成器目標 1;判別更新停止生成梯度。原文 minimax 簡寫不等於實際更新,官方 GANLoss 用平均 L1 [73]、[74]。3,000 次交替,Adam [64]、2×10−42\times10^{-4} 及衰減排程,偏好梯度豐富裁切。

判別器。 不降取樣的全卷積,一個 7 × 7 加六個 1 × 1,頻譜正規化 [36]、BN、ReLU、末 sigmoid。每個判斷只看 7 × 7 區塊,輸出空間 D-map 與逐點標籤。

深線性生成器。 不使用非線性,避免只拼有效區塊來騙判別器。單一卷積本可表達線性縮圖,深分解則在原實驗更好最佳化,不保證核唯一。五個 64 通道隱藏卷積,前核 7/5/3、後為 1,總感受野 13 × 13。初期用 bicubic 輸出作起始約束。

讀出核。 以 stride 1 串起所有生成卷積得可微有效核 kk,加入:

R=αLsum_to_1+βLboundaries+γLsparse+δLcenter,α=0.5, β=0.5, γ=5, δ=1,R = \alpha \mathcal L_{\text{sum\_to\_1}} + \beta \mathcal L_{\text{boundaries}} + \gamma \mathcal L_{\text{sparse}} + \delta \mathcal L_{\text{center}}, \qquad \alpha = 0.5,\ \beta = 0.5,\ \gamma = 5,\ \delta = 1,

Lsum_to_1=∣1−∑kij∣\mathcal L_{\mathrm{sum\_to\_1}}=|1-\sum k_{ij}| 保和一;Lboundaries=∑∣kijmij∣\mathcal L_{\mathrm{boundaries}}=\sum|k_{ij}m_{ij}| 以遠距增長遮罩懲罰邊緣;Lsparse=∑∣kij∣1/2\mathcal L_{\mathrm{sparse}}=\sum|k_{ij}|^{1/2} 抑制過平滑;重心與 (x0,y0)(x_0,y_0) 的 L2 距離約束居中。官方 [73] 改為倍率相依中心、中心 MSE、稀疏指數 0.2 而非原式 0.5,且係數有排程;重現須匹配版本。

×2 到 ×4。 只學 k2k_2,用 k4=k2⊛k2dilk_4=k_2\circledast k_2^{\mathrm{dil}},其中 k2dil[n1,n2]k_2^{\mathrm{dil}}[n_1,n_2] 在兩索引偶數時等於 k2[n1/2,n2/2]k_2[n_1/2,n_2/2]、否則零,避免在過小 ×4 圖訓練。

DIV2KRK。 DIV2K 100 張驗證,11 × 11 非等向高斯,軸寬 U(0.6,5)U(0.6,5)、角度 U[−π,π]U[-\pi,\pi],再乘最多 25% 均勻擾動、正規化並抽取。用來避免舊實拍基準錯位偏袒模糊。

結果

KernelGAN+ZSSR 的 ×2/×4 PSNR/SSIM 為 30.363/0.8669、26.810/0.7316;RCAN+ 29.198/0.8223、25.659/0.6936,bicubic 28.731/0.8040、25.330/0.6795。舊盲賽冠軍 ×4 26.340/0.7190。換早期核+ZSSR 為 29.368/26.080 dB;真核上界 32.436/27.527。KernelGAN+SRMD ×4 25.711/0.7265,PSNR 與 SSIM 排名不同。V100 每圖 61 秒、K80 102 秒,固定裁切訓練預算不隨圖大小直接增加。

消融實驗

  • 單層線性生成器比深層差 3.8 dB/1.6 dB(×2/×4)。
  • 固定 SR 方法換核,品質依 bicubic、Michaeli–Irani、KernelGAN、真核逐步改善。
  • 四核約束的消融只在專案網站,非正文,不補造原文數字。

結論

深線性、逐圖 GAN 可從跨尺度區塊估核,再交非盲模型;原基準仍有距真核的差距。

限制與問題

  • 逐圖約一分鐘,還須 SR;DAN 測 KernelGAN+ZSSR 415.7 秒,前饋估計快得多。
  • 雜訊/JPEG 不符合純縮圖模型。
  • 假設區塊重複及單一空間核,非重複或變化模糊較難。
  • 估計器與復原器分開仍可能失配;DAN 報 KernelGAN+USRNet 在 DIV2KRK ×4 20.06 dB。

參考文獻

  1. N. Efrat, D. Glasner, A. Apartsin, B. Nadler and A. Levin, “Accurate Blur Models vs. Image Priors in Single Image Super-Resolution,” in Proc. IEEE ICCV, 2013, pp. 2832–2839. doi · CVF
  2. K. Zhang, W. Zuo and L. Zhang, “Learning a Single Convolutional Super-Resolution Network for Multiple Degradations,” CVPR, 2018. paper
  3. A. Liu, Y. Liu, J. Gu, Y. Qiao, C. Dong, “Blind Image Super-Resolution: A Survey and Beyond,” IEEE TPAMI (early access), 2022. source
  4. Honggang Chen, Xiaohai He, Linbo Qing, Yuanyuan Wu, Chao Ren, Ray E. Sheriff, Ce Zhu, “Real-world single image super-resolution: A brief review,” Information Fusion, 2022. source
  5. B. B. Moser, A. S. Shanbhag, F. Raue, S. Frolov, S. Palacio and A. Dengel, “Diffusion Models, Image Super-Resolution, and Everything: A Survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 7, pp. 11793–11813, 2025. doi · arXiv
  6. Y. Xu, S. R. Tseng, Y. Tseng, H. Kuo, Y. Tsai, “Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations,” CVPR, 2020. source
  7. K. Zhang, L. Van Gool, R. Timofte, “Deep Unfolding Network for Image Super-Resolution,” CVPR, 2020. source
  8. J. Gu, H. Lu, W. Zuo and C. Dong, “Blind Super-Resolution With Iterative Kernel Correction,” CVPR, 2019. paper
  9. Z. Luo, Y. Huang, S. Li, L. Wang and T. Tan, “Unfolding the Alternating Optimization for Blind Super Resolution,” NeurIPS, 2020. paper
  10. Z. Luo, H. Huang, L. Yu, Y. Li, H. Fan and S. Liu, “Deep Constrained Least Squares for Blind Image Super-Resolution,” CVPR, 2022. paper
  11. T. Michaeli, M. Irani, “Nonparametric Blind Super-resolution,” Proceedings of the IEEE International Conference on Computer Vision, 2013. source
  12. S. Bell-Kligler, A. Shocher and M. Irani, “Blind Super-Resolution Kernel Estimation using an Internal-GAN,” NeurIPS, 2019. paper
  13. A. Shocher, N. Cohen and M. Irani, “‘Zero-Shot’ Super-Resolution Using Deep Internal Learning,” in Proc. IEEE/CVF CVPR, 2018, pp. 3118–3126. doi · arXiv
  14. L. Wang, Y. Wang, X. Dong, Q. Xu, J. Yang, W. An and Y. Guo, “Unsupervised Degradation Representation Learning for Blind Super-Resolution,” CVPR, 2021. paper
  15. B. Xia, Y. Zhang, Y. Wang, Y. Tian, W. Yang, R. Timofte and L. Van Gool, “Knowledge Distillation Based Degradation Estimation for Blind Super-Resolution,” ICLR, 2023. paper
  16. K. Zhang, J. Liang, L. Van Gool, R. Timofte, “Designing a Practical Degradation Model for Deep Blind Image Super-Resolution,” Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021. source
  17. X. Wang, L. Xie, C. Dong, Y. Shan, “Real-ESRGAN: Training Real-World Blind Super-Resolution With Pure Synthetic Data,” Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021. source
  18. J. Liang, H. Zeng, L. Zhang, “Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution,” ECCV, 2022. source
  19. J. Cai, H. Zeng, H. Yong, Z. Cao, L. Zhang, “Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model,” Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. source
  20. P. Wei, Z. Xie, H. Lu, Z. Zhan, Q. Ye, W. Zuo, L. Lin, “Component Divide-and-Conquer for Real-World Image Super-Resolution,” ECCV, 2020. source
  21. C. Chen, Z. Xiong, X. Tian, Z. Zha, F. Wu, “Camera Lens Super-Resolution,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. source
  22. Y. Yuan, S. Liu, J. Zhang, Y. Zhang, C. Dong, L. Lin, “Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks,” CVPR Workshops, 2018. source
  23. A. Bulat, J. Yang, G. Tzimiropoulos, “To learn image super-resolution, use a GAN to learn how to do image degradation first,” ECCV, 2018. source
  24. M. Fritsche, S. Gu, R. Timofte, “Frequency Separation for Real-World Super-Resolution,” ICCV Workshops, 2019. source
  25. X. Ji, Y. Cao, Y. Tai, C. Wang, J. Li, F. Huang, “Real-World Super-Resolution via Kernel Estimation and Noise Injection,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. source
  26. J. Wang, Z. Yue, S. Zhou, K. C. K. Chan, C. C. Loy, “Exploiting Diffusion Prior for Real-World Image Super-Resolution,” IJCV, 2024. source
  27. X. Lin, J. He, Z. Chen, et al., “DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior,” ECCV, 2024. source
  28. T. Yang, R. Wu, P. Ren, X. Xie, L. Zhang, “Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization,” ECCV, 2024. source
  29. R. Wu, T. Yang, L. Sun, Z. Zhang, S. Li, L. Zhang, “SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024. source · supplementary experiments
  30. F. Yu, J. Gu, Z. Li, et al., “Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild,” CVPR, 2024. source
  31. Z. Yue, J. Wang, C. C. Loy, “ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting,” NeurIPS, 2023. source
  32. X. Wang, K. Yu, C. Dong, C. C. Loy, “Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. source
  33. K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, “Momentum Contrast for Unsupervised Visual Representation Learning,” CVPR, 2020. source
  34. X. Wang, K. Yu, S. Wu, J. Gu, Y. Liu, C. Dong, Y. Qiao and C. C. Loy, “ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks,” in Proc. ECCV Workshops, 2018 (Lecture Notes in Computer Science, 2019), pp. 63–79. doi · arXiv
  35. O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Proc. MICCAI, 2015, pp. 234–241. doi · arXiv
  36. T. Miyato, T. Kataoka, M. Koyama, Y. Yoshida, “Spectral Normalization for Generative Adversarial Networks,” ICLR, 2018. source
  37. J. Liang, H. Zeng, L. Zhang, “Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022. source
  38. A. Ignatov, N. Kobyshev, R. Timofte, K. Vanhoey, L. Van Gool, “DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks,” ICCV, 2017. source
  39. A. Lugmayr, M. Danelljan, R. Timofte, “Unsupervised Learning for Real-World Super-Resolution,” arXiv preprint, 2019. source
  40. A. Lugmayr, M. Danelljan, R. Timofte, et al., “NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results,” CVPR Workshops, 2020. source
  41. R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, “High-Resolution Image Synthesis with Latent Diffusion Models,” CVPR, 2022. source
  42. L. Zhang, A. Rao, M. Agrawala, “Adding Conditional Control to Text-to-Image Diffusion Models,” ICCV, 2023. source
  43. Y. Ai, X. Zhou, H. Huang, X. Han, Z. Chen, Q. You, H. Yang, “DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation,” NeurIPS, 2024. source
  44. Z. Duan, J. Zhang, X. Jin, et al., “DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution,” ICCV, 2025. source
  45. R. Wu, L. Sun, Z. Ma, L. Zhang, “One-Step Effective Diffusion Network for Real-World Image Super-Resolution,” NeurIPS, 2024. source
  46. Y. Wang, W. Yang, X. Chen, et al., “SinSR: Diffusion-Based Image Super-Resolution in a Single Step,” CVPR, 2024. source
  47. E. Agustsson and R. Timofte, “NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study,” in Proc. IEEE CVPR Workshops, 2017, pp. 1122–1131. doi · CVF
  48. 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
  49. 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, pp. 586–595. doi · arXiv
  50. K. Ding, K. Ma, S. Wang, E. P. Simoncelli, “Image Quality Assessment: Unifying Structure and Texture Similarity,” IEEE TPAMI, 2022. source
  51. 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
  52. J. Ke, Q. Wang, Y. Wang, P. Milanfar, F. Yang, “MUSIQ: Multi-scale Image Quality Transformer,” ICCV, 2021. source
  53. S. Yang, T. Wu, S. Shi, S. Lao, Y. Gong, M. Cao, J. Wang, Y. Yang, “MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment,” CVPR Workshops, 2022. source
  54. J. Wang, K. C. K. Chan, C. C. Loy, “Exploring CLIP for Assessing the Look and Feel of Images,” AAAI, 2023. source
  55. M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, S. Hochreiter, “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” NeurIPS, 2017. source
  56. R. Timofte, S. Gu, J. Wu, L. Van Gool, “NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018. source
  57. J. Cai, S. Gu, R. Timofte, L. Zhang, “NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. source
  58. A. Lugmayr, M. Danelljan, R. Timofte, et al., “AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results,” ICCV Workshops, 2019. source
  59. P. Wei, H. Lu, R. Timofte, et al., “AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results,” ECCV Workshops, 2020. source
  60. Z. Chen, K. Liu, J. Gong, J. Wang, L. Sun, Z. Wu, R. Timofte, Y. Zhang et al., “NTIRE 2025 Challenge on Image Super-Resolution (×4): Methods and Results,” in Proc. IEEE/CVF CVPR Workshops, 2025, pp. 1525–1535. doi · arXiv
  61. Le Zhang, Ao Li, Qibin Hou, Ce Zhu, Yonina C. Eldar, “Deep-Learning-Empowered Super Resolution: A Comprehensive Survey and Future Prospects,” Proceedings of the IEEE, 2025. source
  62. W. Ren, R. Goyal, Z. Hu, T. T. Aumentado-Armstrong, I. Mohomed and A. Levinshtein, “Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution,” arXiv:2507.14367, 2025. arXiv
  63. Real-ESRGAN contributors, “Real-ESRGAN model and ×4-plus training configuration,” official source, accessed 2026-11-02. model · configuration
  64. D. P. Kingma, J. Ba, “Adam: A Method for Stochastic Optimization,” ICLR, 2015. source
  65. M. Bevilacqua, A. Roumy, C. Guillemot and M.-L. Alberi Morel, “Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding,” in Proc. BMVC, 2012, pp. 135.1–135.10. doi
  66. R. Zeyde, M. Elad and M. Protter, “On Single Image Scale-Up Using Sparse-Representations,” in Curves and Surfaces, Lecture Notes in Computer Science, Springer, 2012, pp. 711–730. doi
  67. D. Martin, C. Fowlkes, D. Tal and J. Malik, “A Database of Human Segmented Natural Images and Its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics,” in Proc. IEEE ICCV, 2001, vol. 2, pp. 416–423. doi
  68. J.-B. Huang, A. Singh and N. Ahuja, “Single Image Super-Resolution from Transformed Self-Exemplars,” in Proc. IEEE CVPR, 2015, pp. 5197–5206. doi · CVF
  69. J. Kim, J. K. Lee and K. M. Lee, “Accurate Image Super-Resolution Using Very Deep Convolutional Networks,” in Proc. IEEE CVPR, 2016, pp. 1646–1654. doi · arXiv
  70. 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, pp. 105–114. doi · arXiv
  71. R. Timofte, E. Agustsson, L. Van Gool, M.-H. Yang, L. Zhang et al., “NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results,” in Proc. IEEE CVPR Workshops, 2017, pp. 1110–1121. doi · CVF
  72. Y. Matsui, K. Ito, Y. Aramaki, A. Fujimoto, T. Ogawa, T. Yamasaki and K. Aizawa, “Sketch-Based Manga Retrieval Using Manga109 Dataset,” Multimedia Tools and Applications, vol. 76, no. 20, pp. 21811–21838, 2017. doi
  73. KernelGAN contributors, “Adversarial losses and kernel constraints,” official source, accessed 2026-11-02. loss definitions · alternating updates
  74. X. Mao, Q. Li, H. Xie, R. Y. K. Lau, Z. Wang, S. P. Smolley, “Least Squares Generative Adversarial Networks,” ICCV, 2017. source
  75. DASR contributors, “MoCo logits and contrastive cross-entropy implementation,” official DASR source, commit 51524af8021c94a502ee002e135867a1b75dc7d0, accessed 2026-11-02. encoder · loss
  76. 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, pp. 294–310. doi · arXiv
  77. K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” in Proc. ICLR, 2015. arXiv
  78. Y. Zhang, X. Huang, J. Ma, et al., “Recognize Anything: A Strong Image Tagging Model,” CVPR Workshops, 2024. source
  79. E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, W. Chen, “LoRA: Low-Rank Adaptation of Large Language Models,” ICLR, 2022. source
  80. D. Podell, Z. English, K. Lacey, A. Blattmann, T. Dockhorn, J. Müller, J. Penna, R. Rombach, “SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis,” ICLR, 2024. source
  81. H. Liu, C. Li, Q. Wu, Y. J. Lee, “Visual Instruction Tuning,” NeurIPS, 2023. source
  82. T. Karras, M. Aittala, T. Aila, S. Laine, “Elucidating the Design Space of Diffusion-Based Generative Models,” NeurIPS, 2022. source