SOURCE-LINKED INTELLIGENCE

Spatially Adaptive Noise Injection

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Diffusion samplers reverse a learned noising process using either stochastic (DDPM) or deterministic (DDIM) updates, which represent endpoints of a single family controlled by a scalar noise-injection variance that is applied identically at every spatial location. This uniform approach neglects the geometry of natural images: high-curvature regions such as edges and textures, where the denoiser is uncertain, benefit from stochastic correction, whereas smooth regions, where the score is precise, are degraded by injected noise. This work investigates whether each pixel requires stochastic correc

Read original source ↗ Open in workspace

recordType

paper

region

Global