完整搜尋頁面 →

TSD-SR:目標感知分數正規化(CVPR 2025)

選讀・DLCV 09A.2・單步擴散超解析度 的論文導讀(第 5/8 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 · 2

  1. 潛在起點不等於加雜訊方程式
  2. 分數正規化與逐圖量測一致性

論文導讀 · 8

  1. ResShift:復原條件的短鏈(NeurIPS 2023)
  2. SinSR:蒸餾確定性的影像條件映射(CVPR 2024)
  3. OSEDiff:LR 潛在起點與變分分數正規化(NeurIPS 2024)
  4. S3Diff:退化引導的低秩調適
  5. TSD-SR:目標感知分數正規化(CVPR 2025)
  6. InvSR:學得的影像條件起點(CVPR 2025)
  7. PiSA-SR:分開像素與語意調適(CVPR 2025)
  8. AddSR:預測細化的對抗復原蒸餾

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

學生輸出差時,強教師也可能給不可靠方向。TSD-SR [6] 在訓練使用配對 HR,改善分數訊號,而非只看教師對生成樣本的預測。

它也以分布感知抽樣強調較難的細節形成狀態,不只均勻抽時間再獨立加雜訊。HR 與額外軌跡只在訓練可用。

方法

區分學生預測、目標感知分數引導與學得的輔助分數;箭頭顯示哪些模型提供梯度、哪些參數會更新。
原論文圖 2 — 區分學生預測、目標感知分數引導與學得的輔助分數;箭頭顯示哪些模型提供梯度、哪些參數會更新。

圖片來源: [6], arXiv:2411.18263v4, PDF 第 3 頁. 原始 PDF.

學生及分數模型。 GθG_\theta 預測 HR 潛在向量 z^\widehat z,凍結教師提供先驗,低秩調適模型估計學生分布。主實驗使用預訓練流匹配骨幹 [35],另比較較小骨幹;調適學生編碼器/去雜訊器,固定解碼器。

一般變分訊號。 對 z^t\widehat z_t,教師與生成分布模型的預測差提供先驗梯度,角色類似 OSEDiff。可靠性取決於它們是否理解實際生成狀態,不能因教師強就假設任何劣質樣本上都校準良好。

目標分數比較。 編碼配對 HR 為 zz 並加雜訊成 ztz_t,比較教師在 z^t\widehat z_t 與 ztz_t 的預測;方向含 ϵψ(z^t,t,c)−ϵψ(zt,t,c)\epsilon_\psi(\widehat z_t,t,c)-\epsilon_\psi(z_t,t,c),ψ\psi 為固定教師,cc 是訓練文字條件。這是配對訊號,不是任意同分布點的分數都應相等。

合併方向。 目標分數與 VSD 結合,一種表示為:

gt=ϵψ(z^t,t,c)−ϵψ(zt,t,c)+λ(ϵψ(zt,t,c)−ϵϕ(z^t,t,c)).g_t=\epsilon_\psi(\widehat z_t,t,c)-\epsilon_\psi(z_t,t,c) +\lambda\bigl(\epsilon_\psi(z_t,t,c)-\epsilon_\phi(\widehat z_t,t,c)\bigr).

ϕ\phi 是調適生成分布模型,λ\lambda 平衡兩項;再乘時間權重與學生參數 Jacobian 得更新。特定端點權重化為一般分數差,中間值引入 HR 資訊。它仍是梯度目標,不是明算乾淨密度。

分布感知抽樣。 從吵的生成/HR 潛在狀態出發,用短調適去雜訊轉移形成多個正規化狀態並累積梯度。狀態數與間隔影響訓練成本,更多不必然更好。

其他監督。 結合像素 LPIPS、潛在 MSE 與目標分數;輔助模型另做擴散訓練,先穩定基本目標,再加入完整抽樣。教師訓練提示可來自 HR,部署學生用預設提示,不能把訓練圖看成推論必須擷取 HR 描述。

結果

主模型 RealSR 的 PSNR/LPIPS/DISTS/FID/MUSIQ 為 24.81/0.2743/0.2104/114.45/71.19,DIV2K 合成驗證為 23.02/0.2673/0.1821/29.16/71.69。部分感知分數改善,像素保真低於某些基準;主骨幹與 OSEDiff 不同,並非純目標比較。

原文也把方法套到較小先驗,以檢查超出大骨幹本身的效果。無參考與偏好仍只衡量所測影像,不證明恢復所有真實細節。

消融實驗

DRealSR 移除目標分數的 LPIPS/DISTS/MUSIQ 0.3176/0.2327/63.90;移除分布抽樣 0.3097/0.2311/63.56;完整 0.2967/0.2136/66.62。RealSR LPIPS 對應 0.2934/0.2873/0.2743,支持兩元件在該設定皆有貢獻。

固定間隔抽 2/4/8 狀態時,DRealSR LPIPS 0.3104/0.2967/0.3421。更多狀態反而可能變差;這些是正規化訓練狀態,不是部署 SR 步數。

結論

配對 HR 改善教師先驗方向,軌跡感知狀態改變施加方向的位置。方法針對分數目標及訓練分布,不只是增加推論預算。

限制與問題

仍須配對資料、輔助模型與額外轉移;分數是近似,目標感知不會替新輸入創造 HR 證據。大骨幹若無控制會混合容量與目標;保真、外觀與語意仍可能衝突。

參考文獻

  1. R. Wu, L. Sun, Z. Ma, L. Zhang, “One-Step Effective Diffusion Network for Real-World Image Super-Resolution,” NeurIPS, 2024. source
  2. Z. Yue, J. Wang, C. C. Loy, “ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting,” NeurIPS, 2023. source
  3. Y. Wang, W. Yang, X. Chen, et al., “SinSR: Diffusion-Based Image Super-Resolution in a Single Step,” CVPR, 2024. source · supplementary ablations
  4. A. Zhang, Z. Yue, R. Pei, W. Ren, X. Cao, “Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors,” arXiv preprint, 2024. paper
  5. Y. Tai, R. Xie, C. Zhao, K. Zhang, Z. Zhang, J. Zhou, J. Yang, “AddSR: Accelerating diffusion-based blind super-resolution with adversarial diffusion distillation,” Pattern Recognition, 2026. published version · manuscript supplying the discussed tables
  6. L. Dong, Q. Fan, Y. Guo, Z. Wang, Q. Zhang, J. Chen, Y. Luo, C. Zou, “TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution,” CVPR, 2025. paper
  7. Z. Yue, K. Liao, C. C. Loy, “Arbitrary-steps Image Super-resolution via Diffusion Inversion,” CVPR, 2025. paper
  8. L. Sun, R. Wu, Z. Ma, S. Liu, Q. Yi, L. Zhang, “Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach,” CVPR, 2025. paper
  9. A. Liu, Y. Liu, J. Gu, Y. Qiao, C. Dong, “Blind Image Super-Resolution: A Survey and Beyond,” IEEE TPAMI (early access), 2022. source
  10. 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
  11. 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
  12. 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
  13. Z. Wang, C. Lu, Y. Wang, F. Bao, C. Li, H. Su, J. Zhu, “ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation,” NeurIPS, 2023. paper
  14. A. Sauer, D. Lorenz, A. Blattmann, R. Rombach, “Adversarial Diffusion Distillation,” ECCV, 2024. paper
  15. 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
  16. 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
  17. 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
  18. 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
  19. K. Ding, K. Ma, S. Wang, E. P. Simoncelli, “Image Quality Assessment: Unifying Structure and Texture Similarity,” IEEE TPAMI, 2022. source
  20. 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
  21. J. Ke, Q. Wang, Y. Wang, P. Milanfar, F. Yang, “MUSIQ: Multi-scale Image Quality Transformer,” ICCV, 2021. source
  22. 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
  23. J. Wang, K. C. K. Chan, C. C. Loy, “Exploring CLIP for Assessing the Look and Feel of Images,” AAAI, 2023. source
  24. X. Fan, Z. Wu, H. Wu, L. Cao, “A Survey on Pre-Trained Diffusion Model Distillations,” arXiv preprint, version 2, 2025. paper
  25. Z. Wu, Y. Dong, X. Wei, “TUDSR: Twice Upsampling-Diffusion for Higher Super-Resolution,” CVPR, 2026. paper
  26. P. Esser, R. Rombach, B. Ommer, “Taming Transformers for High-Resolution Image Synthesis,” CVPR, 2021. paper
  27. 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
  28. J. Deng, W. Dong, R. Socher, L. Li, Kai Li, Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” CVPR, 2009. doi
  29. R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, “High-Resolution Image Synthesis with Latent Diffusion Models,” CVPR, 2022. source
  30. 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
  31. H. Liu, C. Li, Q. Wu, Y. J. Lee, “Visual Instruction Tuning,” NeurIPS, 2023. source
  32. Y. Li, K. Zhang, J. Liang, et al., “LSDIR: A Large Scale Dataset for Image Restoration,” CVPR Workshops, 2023. paper
  33. T. Karras, S. Laine, T. Aila, “A Style-Based Generator Architecture for Generative Adversarial Networks,” CVPR, 2019. paper
  34. I. Loshchilov, F. Hutter, “Decoupled Weight Decay Regularization,” ICLR, 2019. paper
  35. P. Esser, S. Kulal, A. Blattmann, et al., “Scaling Rectified Flow Transformers for High-Resolution Image Synthesis,” ICML, 2024. paper
  36. J. Ho, T. Salimans, “Classifier-Free Diffusion Guidance,” arXiv preprint, 2022. paper
  37. 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