Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score 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_ | 1866915206475546624 |
|---|---|
| author | Liu, Kendong Zhu, Zhiyu Liu, Hui Hou, Junhui |
| author_facet | Liu, Kendong Zhu, Zhiyu Liu, Hui Hou, Junhui |
| contents | We present Acc3D to tackle the challenge of accelerating the diffusion process to generate 3D models from single images. To derive high-quality reconstructions through few-step inferences, we emphasize the critical issue of regularizing the learning of score function in states of random noise. To this end, we propose edge consistency, i.e., consistent predictions across the high signal-to-noise ratio region, to enhance a pre-trained diffusion model, enabling a distillation-based refinement of the endpoint score function. Building on those distilled diffusion models, we propose an adversarial augmentation strategy to further enrich the generation detail and boost overall generation quality. The two modules complement each other, mutually reinforcing to elevate generative performance. Extensive experiments demonstrate that our Acc3D not only achieves over a $20\times$ increase in computational efficiency but also yields notable quality improvements, compared to the state-of-the-arts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation Liu, Kendong Zhu, Zhiyu Liu, Hui Hou, Junhui Computer Vision and Pattern Recognition We present Acc3D to tackle the challenge of accelerating the diffusion process to generate 3D models from single images. To derive high-quality reconstructions through few-step inferences, we emphasize the critical issue of regularizing the learning of score function in states of random noise. To this end, we propose edge consistency, i.e., consistent predictions across the high signal-to-noise ratio region, to enhance a pre-trained diffusion model, enabling a distillation-based refinement of the endpoint score function. Building on those distilled diffusion models, we propose an adversarial augmentation strategy to further enrich the generation detail and boost overall generation quality. The two modules complement each other, mutually reinforcing to elevate generative performance. Extensive experiments demonstrate that our Acc3D not only achieves over a $20\times$ increase in computational efficiency but also yields notable quality improvements, compared to the state-of-the-arts. |
| title | Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15975 |