Mean-Shift Distillation for Diffusion Mode Seeking
원문 초록
We present mean-shift distillation, a novel diffusion distillation technique that provides a provably good proxy for the gradient of the diffusion output distribution. This is derived directly from mean-shift mode seeking on the distribution, and we show that its extrema are aligned with the modes. We further derive an efficient product distribution sampling procedure to evaluate the gradient. Our method is formulated as a drop-in replacement for score distillation sampling (SDS), requiring neither model retraining nor extensive modification of the sampling procedure. We show that it exhibits superior mode alignment as well as improved convergence in both synthetic and practical setups, yielding higher-fidelity results when applied to both text-to-image and text-to-3D applications with Stable Diffusion.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generating Physically Stable and Buildable LEGO Designs from Text
Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation
SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models
DiMeR: Disentangled Mesh Reconstruction Model
Text-based Animatable 3D Avatars with Morphable Model Alignment
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.