We present a novel physics-informed neural network (PINN) for the direct estimation of the continuous soil particle size distribution curve (PSD) from visible–near infrared (vis-NIR) reflectance measurements. Unlike traditional methods that focus on predicting soil fractions (e.g., sand, silt, and clay), the PINN takes in the soil particle size as a predictor and learns a continuous, differentiable, and non-parametric representation of the cumulative PSD by integrating both measurements and physical constraints imposed during training. This approach eliminates the need for harmonization and interpolation of measurements originating from different soil texture classification systems and allows the model to be trained on datasets with varying number of measurements per sample. Performance evaluation on 30% of the 2,777 studied samples showed that the PINN achieved an RMSE of 6.77% and an R² of 0.97 in predicting the cumulative PSD fraction. For the texture fractions, the model achieved RMSE values of 4.72%, 3.06%, and 2.75% for sand, silt, and clay, respectively. A comparison with a physics-agnostic (i.e., physics-uninformed) version of the model revealed that both approaches performed similarly in terms of RMSE and R². However, the physics-agnostic model violated physical constraints even in data-rich scenarios. In contrast, the PSD obtained from the PINN maintained its physical integrity even under data sparsity conditions and consistently produced non-negative, monotonically increasing predictions that sum to 100% at the largest particle size.