paper-with-me

홈 › Papers

Flow Score Distillation for Diverse Text-to-3D Generation

2024-05-16 · Runjie Yan, Kailu Wu, Kaisheng Ma

Recent advancements in Text-to-3D generation have yielded remarkable progress, particularly through methods that rely on Score Distillation Sampling (SDS). While SDS exhibits the capability to create impressive 3D assets, it is hindered by its inherent maximum-likelihood-seeking essence, resulting in limited diversity in generation outcomes. In this paper, we discover that the Denoise Diffusion Implicit Models (DDIM) generation process (\ie PF-ODE) can be succinctly expressed using an analogue of SDS loss. One step further, one can see SDS as a generalized DDIM generation process. Following this insight, we show that the noise sampling strategy in the noise addition stage significantly restricts the diversity of generation results. To address this limitation, we present an innovative noise sampling approach and introduce a novel text-to-3D method called Flow Score Distillation (FSD). Our validation experiments across various text-to-image Diffusion Models demonstrate that FSD substantially enhances generation diversity without compromising quality.

📄 PDF Abstract BibTeX arXiv:2405.10988

Code (0)

등록된 구현이 없습니다.

Tasks

3D GenerationDiversityText to 3D

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Score Distillation of Flow Matching Models

2025-09-29 · Mingyuan Zhou, Yi Gu, Huangjie Zheng, Liangchen Song 외 arxiv

Diffusion models achieve high-quality image generation but are limited by slow iterative sampling. Distillation methods alleviate this by enabling one- or few-step generation. Flow matching, originally introduced as a di…

Image Generation

Diverse Score Distillation

2024-12-09 · Yanbo Xu, Jayanth Srinivasa, Gaowen Liu, Shubham Tulsiani

Score distillation of 2D diffusion models has proven to be a powerful mechanism to guide 3D optimization, for example enabling text-based 3D generation or single-view reconstruction. A common limitation of existing score…

3D GenerationDenoisingDiversity

Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models

2026-06-09 · An Zhao, Shengyuan Zhang, Zhongjian Sun, Yixiang Zhou 외 arxiv

Flow Matching models have demonstrated strong performance across a wide range of generative tasks. However, their reliance on ODE-based iterative sampling incurs substantial computational overhead in inference, which lim…

Text-to-Image Generation

Consistent Flow Distillation for Text-to-3D Generation

2025-01-09 · Runjie Yan, Yinbo Chen, Xiaolong Wang

Score Distillation Sampling (SDS) has made significant strides in distilling image-generative models for 3D generation. However, its maximum-likelihood-seeking behavior often leads to degraded visual quality and diversit…

3D GenerationDiversityText to 3D

FlowDreamer: Exploring High Fidelity Text-to-3D Generation via Rectified Flow

2024-08-09 · Hangyu Li, Xiangxiang Chu, Dingyuan Shi, Wang Lin

Recent advances in text-to-3D generation have made significant progress. In particular, with the pretrained diffusion models, existing methods predominantly use Score Distillation Sampling (SDS) to train 3D models such a…

3D GenerationNeRFText to 3D