Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Junhong, Kim, Seungwook, Cho, Minsu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908380507930624
author Lee, Junhong
Kim, Seungwook
Cho, Minsu
author_facet Lee, Junhong
Kim, Seungwook
Cho, Minsu
contents Recent studies show that simple training-free techniques can dramatically improve the quality of text-to-2D generation outputs, e.g. Classifier-Free Guidance (CFG) or FreeU. However, these training-free techniques have been underexplored in the lens of Score Distillation Sampling (SDS), which is a popular and effective technique to leverage the power of pretrained text-to-2D diffusion models for various tasks. In this paper, we aim to shed light on the effect such training-free techniques have on SDS, via a particular application of text-to-3D generation via 2D lifting. We present our findings, which show that varying the scales of CFG presents a trade-off between object size and surface smoothness, while varying the scales of FreeU presents a trade-off between texture details and geometric errors. Based on these findings, we provide insights into how we can effectively harness training-free techniques for SDS, via a strategic scaling of such techniques in a dynamic manner with respect to the timestep or optimization iteration step. We show that using our proposed scheme strikes a favorable balance between texture details and surface smoothness in text-to-3D generations, while preserving the size of the output and mitigating the occurrence of geometric defects.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19868
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling
Lee, Junhong
Kim, Seungwook
Cho, Minsu
Computer Vision and Pattern Recognition
Recent studies show that simple training-free techniques can dramatically improve the quality of text-to-2D generation outputs, e.g. Classifier-Free Guidance (CFG) or FreeU. However, these training-free techniques have been underexplored in the lens of Score Distillation Sampling (SDS), which is a popular and effective technique to leverage the power of pretrained text-to-2D diffusion models for various tasks. In this paper, we aim to shed light on the effect such training-free techniques have on SDS, via a particular application of text-to-3D generation via 2D lifting. We present our findings, which show that varying the scales of CFG presents a trade-off between object size and surface smoothness, while varying the scales of FreeU presents a trade-off between texture details and geometric errors. Based on these findings, we provide insights into how we can effectively harness training-free techniques for SDS, via a strategic scaling of such techniques in a dynamic manner with respect to the timestep or optimization iteration step. We show that using our proposed scheme strikes a favorable balance between texture details and surface smoothness in text-to-3D generations, while preserving the size of the output and mitigating the occurrence of geometric defects.
title Harnessing the Power of Training-Free Techniques in Text-to-2D Generation for Text-to-3D Generation via Score Distillation Sampling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19868