SimStage: Harnessing Video Diffusion for Consistent Virtual Light Stage Synthesis

One-light-at-a-time (OLAT) prediction provides explicit and reusable control for portrait relighting, but its promise depends on recovering an entire lighting basis with both Basis Fidelity and Basis Coherence: each response must preserve accurate HDR appearance, while all responses must remain structurally aligned so that details survive composition. We introduce SimStage, a Full-Basis OLAT Generator that directly predicts all $331$ lighting responses within a single generation window. Our key insight is Light-Axis Rebinding: rather than treating OLATs as independent predictions, we redesign the joint-generation paradigm of video diffusion so that its sequence axis represents illumination instead of time. This is non-trivial—native temporal position modeling fails to reliably learn even substantially shorter OLAT windows. We therefore introduce LiRoPE, which replaces temporal relative positioning with calibrated light-direction geometry and enables full-basis joint generation. Together with an HDR radiance encoding, SimStage produces an integration-ready OLAT basis from a single portrait. Experiments on FaceOLAT improve composited relighting PSNR by $9.16$ dB over 3DPR, while preserving substantially sharper details and accurately controlling shading, cast shadows, and specular highlights.