Machine Heart

May 21, 2026 · Artificial Intelligence

Learning Adaptive Gaussian Sampling for 3D Generation: Density‑Sampled Gaussians (DeG) at SIGGRAPH 2026

The SIGGRAPH 2026 paper “Generative 3D Gaussians with Learned Density Control” introduces Density‑Sampled Gaussians (DeG), a differentiable framework that lets a model learn where to place Gaussian splats by sampling from a learned spatial density, enabling arbitrary‑budget, non‑uniform 3D representations with higher quality per cost.