用奖励模型加权采样，让扩散模型生成更符合用户意图的3D内容。
RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling
- 根据奖励模型得分加权噪声样本，优化梯度方向。
- 在文本到图像、2D编辑和文本到3D生成中显著提升对齐效果。
- 适用于多种基于SDS的方法，适合追求高精度生成的开发者。
Score Distillation Sampling (SDS) 已成为利用2D扩散先验进行文本到3D生成等任务的有效方法。尽管强大，SDS 在实现细粒度用户意图对齐方面仍存在挑战。为此，我们提出 RewardSDS，一种新方法：基于奖励模型的对齐得分对噪声样本进行加权，生成加权的 SDS 损失。该损失优先选择产生高奖励输出的噪声样本所对应的梯度。本方法具有广泛适用性，可扩展至基于 SDS 的各类方法。我们特别将其应用于变分分数蒸馏（VSD），提出 RewardVSD。在文本到图像、2D编辑及文本到3D生成任务上评估表明，RewardSDS 和 RewardVSD 在多项衡量生成质量与对齐奖励模型的指标上均显著优于 SDS 与 VSD，达到当前最优性能。
原文摘要 · Abstract (English)
Score Distillation Sampling (SDS) has emerged as an effective technique for leveraging 2D diffusion priors for tasks such as text-to-3D generation. While powerful, SDS struggles with achieving fine-grained alignment to user intent. To overcome this, we introduce RewardSDS, a novel approach that weights noise samples based on alignment scores from a reward model, producing a weighted SDS loss. This loss prioritizes gradients from noise samples that yield aligned high-reward output. Our approach is broadly applicable and can extend SDS-based methods. In particular, we demonstrate its applicability to Variational Score Distillation (VSD) by introducing RewardVSD. We evaluate RewardSDS and RewardVSD on text-to-image, 2D editing, and text-to-3D generation tasks, showing significant improvements over SDS and VSD on a diverse set of metrics measuring generation quality and alignment to desired reward models, enabling state-of-the-art performance. Project page is available at https://itaychachy.github.io/reward-sds/.
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。