用边缘一致性加速单图生成3D模型，效率提升20倍以上。
Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation
- 通过边缘一致性约束噪声状态下的得分函数学习。
- 实现20倍以上计算效率提升，生成质量显著优于现有方法。
- 适合需要快速高质量3D生成的工业与设计场景。
我们提出Acc3D，以解决从单张图像生成3D模型时扩散过程过慢的问题。为在少步推理中获得高质量重建，关键在于对随机噪声状态下的得分函数学习进行正则化。为此，我们引入边缘一致性——在高信噪比区域保持预测一致，用于增强预训练扩散模型，实现基于蒸馏的终点得分函数优化。在此基础上，我们提出对抗性增强策略，进一步丰富生成细节并提升整体质量。两个模块相互补充，协同提升生成性能。大量实验表明，Acc3D不仅实现超过20倍的计算效率提升，且生成质量显著优于当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。