SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918111348785152 |
|---|---|
| author | Zhu, Jiahao Chen, Zixuan Wang, Guangcong Xie, Xiaohua Zhou, Yi |
| author_facet | Zhu, Jiahao Chen, Zixuan Wang, Guangcong Xie, Xiaohua Zhou, Yi |
| contents | Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between self-consistency and cross-consistency, these CD-based methods inherently suffer from improper conditional guidance, leading to sub-optimal generation results. To address this issue, we present SegmentDreamer, a novel framework designed to fully unleash the potential of consistency models for high-fidelity text-to-3D generation. Specifically, we reformulate SDS through the proposed Segmented Consistency Trajectory Distillation (SCTD), effectively mitigating the imbalance issues by explicitly defining the relationship between self- and cross-consistency. Moreover, SCTD partitions the Probability Flow Ordinary Differential Equation (PF-ODE) trajectory into multiple sub-trajectories and ensures consistency within each segment, which can theoretically provide a significantly tighter upper bound on distillation error. Additionally, we propose a distillation pipeline for a more swift and stable generation. Extensive experiments demonstrate that our SegmentDreamer outperforms state-of-the-art methods in visual quality, enabling high-fidelity 3D asset creation through 3D Gaussian Splatting (3DGS). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05256 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation Zhu, Jiahao Chen, Zixuan Wang, Guangcong Xie, Xiaohua Zhou, Yi Computer Vision and Pattern Recognition Recent advancements in text-to-3D generation improve the visual quality of Score Distillation Sampling (SDS) and its variants by directly connecting Consistency Distillation (CD) to score distillation. However, due to the imbalance between self-consistency and cross-consistency, these CD-based methods inherently suffer from improper conditional guidance, leading to sub-optimal generation results. To address this issue, we present SegmentDreamer, a novel framework designed to fully unleash the potential of consistency models for high-fidelity text-to-3D generation. Specifically, we reformulate SDS through the proposed Segmented Consistency Trajectory Distillation (SCTD), effectively mitigating the imbalance issues by explicitly defining the relationship between self- and cross-consistency. Moreover, SCTD partitions the Probability Flow Ordinary Differential Equation (PF-ODE) trajectory into multiple sub-trajectories and ensures consistency within each segment, which can theoretically provide a significantly tighter upper bound on distillation error. Additionally, we propose a distillation pipeline for a more swift and stable generation. Extensive experiments demonstrate that our SegmentDreamer outperforms state-of-the-art methods in visual quality, enabling high-fidelity 3D asset creation through 3D Gaussian Splatting (3DGS). |
| title | SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.05256 |