Exploiting Self-Supervised Constraints in Image Super-Resolution (2404.00260v1)
Abstract: Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing. This paper introduces a novel self-supervised constraint for single image super-resolution, termed SSC-SR. SSC-SR uniquely addresses the divergence in image complexity by employing a dual asymmetric paradigm and a target model updated via exponential moving average to enhance stability. The proposed SSC-SR framework works as a plug-and-play paradigm and can be easily applied to existing SR models. Empirical evaluations reveal that our SSC-SR framework delivers substantial enhancements on a variety of benchmark datasets, achieving an average increase of 0.1 dB over EDSR and 0.06 dB over SwinIR. In addition, extensive ablation studies corroborate the effectiveness of each constituent in our SSC-SR framework. Codes are available at https://github.com/Aitical/SSCSR.
- “From beginner to master: A survey for deep learning-based single-image super-resolution,” CoRR, vol. abs/2109.14335, 2021.
- “A deep journey into super-resolution: A survey,” ACM Comput. Surv., 2020.
- “Enhanced deep residual networks for single image super-resolution,” in CPVR, 2017.
- “Image super-resolution using very deep residual channel attention networks,” in ECCV, 2018.
- “Image super-resolution with non-local sparse attention,” in CVPR, 2021.
- “SwinIR: Image restoration using swin transformer,” in ICCVW, 2021.
- “Activating more pixels in image super-resolution transformer,” in CVPR, 2023.
- “A survey of self-supervised learning from multiple perspectives: Algorithms, theory, applications and future trends,” CoRR, vol. abs/2301.05712, 2023.
- “Contrastive learning for compact single image dehazing,” in CVPR, 2021.
- “A practical contrastive learning framework for single-image super-resolution,” IEEE TNNLS, pp. 1–12, 2023.
- “Learning from history: Task-agnostic model contrastive learning for image restoration,” in AAAI, 2024.
- “Image super-resolution using deep convolutional networks,” IEEE TPAMI, vol. 38, no. 2, pp. 295–307, 2016.
- “Second-order attention network for single image super-resolution,” in CVPR, 2019.
- “Single image super-resolution via a holistic attention network,” in ECCV, 2020.
- “Fully 1×1 convolutional network for lightweight image super-resolution,” CoRR, vol. abs/2307.16140, 2023.
- “Atmfn: Adaptive-threshold-based multi-model fusion network for compressed face hallucination,” IEEE TMM, vol. 22, no. 10, pp. 2734–2747, 2020.
- “Dual-path deep fusion network for face image hallucination,” IEEE TNNLS, vol. 33, no. 1, pp. 378–391, 2022.
- “Rain-free and residue hand-in-hand: A progressive coupled network for real-time image deraining,” IEEE TIP, vol. 30, pp. 7404–7418, 2021.
- “Momentum contrast for unsupervised visual representation learning,” in CVPR, 2020.
- “A simple framework for contrastive learning of visual representations,” in ICML, 2020.
- “Zero-mean regularized spectral contrastive learning: Implicitly mitigating wrong connections in positive-pair graphs,” in ICLR, 2024.
- “Curricular contrastive regularization for physics-aware single image dehazing,” in CVPR. 2023, pp. 5785–5794, IEEE.
- “Harnessing joint rain-/detail-aware representations to eliminate intricate rains,” in ICLR, 2024.
- “Cross-scale internal graph neural network for image super-resolution,” in NeurIPS, 2020.