AI RESEARCH
Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
arXiv CS.CV
•
ArXi:2605.09071v1 Announce Type: new Score Distillation Sampling (SDS) and its variants have been widely used for text-to-3D generation by distilling 2D image diffusion priors. However, the standard SDS objective is prone to severe mode collapse, frequently yielding over-smoothed and over-saturated results. Although recent advancements, such as Score Distillation via Inversion (SDI), mitigate these artifacts and produce visually sharper models, they ultimately fail to faithfully capture the full target distribution.