Abstract Deep learning has demonstrated remarkable success in augmenting fluorescence imaging under photon-limited conditions. However, existing restoration networks are typically devised for training with augmented patches far smaller than the full-view raw data, an overlooked aspect that compromises fidelity and noise-resistance due to the loss of global statistics. To address this limitation, we propose a large-patch network (LargePNet), which synergizes the large effective receptive field provided by shallow ultra-large-kernel convolutions and the nonlinear representation capabilities of deep networks through scale separation. It effectively and efficiently leverages large-view global information for restoration. Directly trained with large-view images, LargePNet shows contrasting advantages over state-of-the-art small-patch networks, with 0.5-2 dB higher peak signal-to-noise ratio across eight representative restoration tasks, involving implementations for single-image, video, and volumetric fluorescence data. For full-view processing, LargePNet generally holds around 4-fold and 20-fold higher computational efficiency compared to advanced convolution-based and Transformer-based networks, respectively. The assistance of LargePNet helps achieve 30-hour-long fluorescence imaging to monitor cytoskeleton dynamics, and hour-long tri-color super-resolution imaging to investigate organelle interaction, showcasing its advancement in live-cell imaging. Similar content being viewed by others Data availability The open-source data used in this study are all publicly available, as listed in Supplementary Table 15. The self-established dataset of STED denoising/deblurring, virtual sampling of SMLM, volumetric background removal datasets, and the source training data for the open-source BioSR and BioTISR datasets are available: https://zenodo.org/records/15694668. Code availability The source Python code of the LargePNet series, including LargePNet (for single-image restoration), LargeP-GAN (for generative single-image restoration), LargeP-TISR (for time-lapse video restoration), and 3D-LargePNet (for volumetric data restoration) are all publicly available at the GitHub repository56: https://github.com/YiweiHou/LargePNet-for-fluorescence-image-restoration. Trained LargePNet models that can reproduce the results in the paper are available at: https://figshare.com/s/05f576c96b08add7eee0. References Ledig, C. et al. Photo-realistic single image super-resolution using a generative adversarial network. In Proc. IEEE