Belsten and Berkeley neuroscientist Bruno Olshausen demonstrated that the natural world displays a restricted palette of colors that the human brain represents as combinations of only four pure colors. ^[1] Biologists and linguists have long puzzled over the universal human tendency to see and name colors as a combination of four pure hues: red, yellow, green, and blue. ^[2] Researchers present a direct optimization method for three-dimensional freeform reflectors that transform the light of a finite-étendue source into a prescribed far-field angular intensity distribution. ^[3] Most people and most cultures do not perceive red as a combination of orange or purple, whereas they naturally perceive orange as a combination of yellow and red. ^[4] The authors parameterize the emission directions in gnomonic coordinates to ensure that every emitted ray intersects the reflector. ^[5] The method converges reliably within seconds on a single GPU for all examples tested. ^[6] The reflector profile is represented by a small neural network, specifically a multilayer perceptron, which is trained end-to-end through a differentiable ray-tracing objective. ^[7]