Procedural Supervision

Use procedurally generated 3D data with perfect ground truth labels to supervise 3D vision models, bypassing the need for expensive real-world 3D annotation. Procedural supervision generates synthetic 3D training data using rendering engines or procedural generation, providing perfect labels (depth, normals, segmentation, correspondences) at no human cost. The training pipeline renders large volumes of synthetic 3D scenes with varied geometry, materials, and lighting, then uses the automatically-generated labels to supervise 3D backbone networks. Models pretrained this way transfer surprisingly well to real-world 3D tasks.