To propose a quantitative 3D double-echo steady-state (DESS) sequence that offers rapid and repeatable T mapping of the human brain using different encoding schemes that account for respiratory B variation. A retrospective self-gating module was firstly implemented into the standard DESS sequence in order to suppress the respiratory artifact via data binning. A compressed-sensing trajectory (CS-DESS) was then optimized to accelerate the acquisition. Finally, a spiral Cartesian encoding (SPICCS-DESS) was incorporated to further disrupt the coherent respiratory artifact. These different versions were compared to a standard DESS sequence (fully DESS) by assessing the T distribution and repeatability in different brain regions of eight volunteers at 3 T. The respiratory artifact correction was determined to be optimal when the data was binned into seven respiratory phases. Compared to the fully DESS, T distribution was improved for the CS-DESS and SPICCS-DESS with interquartile ranges reduced significantly by a factor ranging from 2 to 12 in the caudate, putamen, and thalamus regions. In the gray and white matter areas, average absolute test-retest T differences across all volunteers were respectively 3.5 ± 2% and 3.1 ± 2.1% for the SPICCS-DESS, 4.6 ± 4.6% and 4.9 ± 5.1% for the CS-DESS, and 15% ± 13% and 7.3 ± 5.6% for the fully DESS. The SPICCS-DESS sequence's acquisition time could be reduced by half (<4 min) while maintaining its efficient T mapping. The respiratory-resolved SPICCS-DESS sequence offers rapid, robust, and repeatable 3D T mapping of the human brain, which can be especially effective for longitudinal monitoring of cerebral pathologies.< Réduire