•A grid-scale temporal downscaling approach based on scale-invariance is proposed.•Sub-daily extreme rainfall intensities are estimated under climate change.•The approach is applied to case studies with a relatively high station density. Canada. Intensity-duration-frequency curves need to be updated to account for the potential effect of climate change. However, sub-daily regional climate model (RCM) simulations required for this purpose are commonly unavailable. The scaling approach is often applied for temporal downscaling of point daily precipitation; nevertheless, difference in spatial scale between simulations and observations may complicate its application at the grid scale. This study proposes a grid-scale temporal downscaling approach for estimating sub-daily gridded extreme rainfall intensity under climate change at regions with a relatively high station density. The approach uses daily annual maximum rainfall intensity series from RCM simulations and grid-scale scaling properties from observations. The study evaluates two methods for estimating gridded scaling exponents needed in temporal downscaling. The assessment is performed on observation-based and RCM-based temporally downscaled quantiles. The effect of temporal downscaling and bias correction on sub-daily quantiles and relative changes is also analysed. The approach is applied to three case studies across Canada. Piecewise simple scaling is found over the study domains, indicating caution in using simple scaling. The performance of the approach in estimating sub-daily observation-based gridded rainfall intensity quantiles is suitable, with preference for point to grid transfer at the annual maximum series stage. Bias correction is necessary for properly estimating sub-daily RCM-based quantiles, presenting less impact on relative changes.