VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914874314981376 |
|---|---|
| author | Zhuo, Wenjie Ma, Fan Fan, Hehe Yang, Yi |
| author_facet | Zhuo, Wenjie Ma, Fan Fan, Hehe Yang, Yi |
| contents | This paper presents Invariant Score Distillation (ISD), a novel method for high-fidelity text-to-3D generation. ISD aims to tackle the over-saturation and over-smoothing problems in Score Distillation Sampling (SDS). In this paper, SDS is decoupled into a weighted sum of two components: the reconstruction term and the classifier-free guidance term. We experimentally found that over-saturation stems from the large classifier-free guidance scale and over-smoothing comes from the reconstruction term. To overcome these problems, ISD utilizes an invariant score term derived from DDIM sampling to replace the reconstruction term in SDS. This operation allows the utilization of a medium classifier-free guidance scale and mitigates the reconstruction-related errors, thus preventing the over-smoothing and over-saturation of results. Extensive experiments demonstrate that our method greatly enhances SDS and produces realistic 3D objects through single-stage optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09822 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation Zhuo, Wenjie Ma, Fan Fan, Hehe Yang, Yi Computer Vision and Pattern Recognition This paper presents Invariant Score Distillation (ISD), a novel method for high-fidelity text-to-3D generation. ISD aims to tackle the over-saturation and over-smoothing problems in Score Distillation Sampling (SDS). In this paper, SDS is decoupled into a weighted sum of two components: the reconstruction term and the classifier-free guidance term. We experimentally found that over-saturation stems from the large classifier-free guidance scale and over-smoothing comes from the reconstruction term. To overcome these problems, ISD utilizes an invariant score term derived from DDIM sampling to replace the reconstruction term in SDS. This operation allows the utilization of a medium classifier-free guidance scale and mitigates the reconstruction-related errors, thus preventing the over-smoothing and over-saturation of results. Extensive experiments demonstrate that our method greatly enhances SDS and produces realistic 3D objects through single-stage optimization. |
| title | VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.09822 |