Over the last years, a very active field of research aims at exploring new data-driven and  learning-based methodologies to propose computationally efficient strategies able to benefit from  the large amount of observational remote sensing and numerical simulations for the reconstruction,  interpolation and prediction of high-resolution derived products of geophysical fields. In this paper,  we investigate how they might help to solve for the oversmoothing of the state-of-the-art optimal  interpolation (OI) techniques in the reconstruction of sea surface height (SSH) spatio-temporal  fields. We focus on two small 10° x 10° GULFSTREAM and 8° x 10° OSMOSIS regions, part  of the North-Atlantic basin: the GULFSTREAM area is mainly driven by energetic mesoscale  dynamics while OSMOSIS is less energetic but with more noticeable small spatial patterns. Based on  Observation System Simulation Experiments (OSSE), we will use the the NATL60 high resolution  deterministic ocean simulation of the North Atlantic to generate two types of pseudo altimetric  observational dataset: along-track nadir data for the current capabilities of the observation system  and wide-swath SWOT data in the context of the upcoming SWOT mission. We briefly introduce  the analog data assimilation (AnDA), an up-to-date version of the DINEOF algorithm, and a new  neural networks-based end-to-end learning framework for the representation of spatio-temporal  irregularly-sampled data. The main objective of this paper consists in providing a thorough  intercomparison exercise with appropriate benchmarking metrics to assess if these approaches  helps to improve the SSH altimetric interpolation problem and to identify which one performs best  in this context. We demonstrate how the newly introduced NN method is a significant improvement  with a plug-and-play implementation and its ability to catch up the small scales ranging up to 40km,  inaccessible by the conventional methods so far. A clear gain is also demonstrated when assimilating  jointly wide-swath SWOT and (agreggated) along-track nadir observations.