提出无需复杂训练的扩散模型采样器，提升生成细节质量
GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
- 用简单参数化方法替代传统复杂训练的扩散ODE求解器
- 结合对抗训练使生成图像细节更清晰，减少伪影
- 在少步采样下优于现有方法，适合高效生成场景
尽管扩散模型已实现顶尖生成质量，其采样过程仍计算昂贵。近期工作通过梯度优化方法，从完整采样过程蒸馏出少步的ODE求解器，将函数评估次数从数十次降至少数次。但这些方法常依赖复杂的训练技巧，且未显式关注细粒度细节保留。本文提出通用求解器：一种无需额外训练技巧的ODE采样器简化参数化方法，在质量上超越现有方案。进一步将原始蒸馏损失与对抗训练结合，有效缓解伪影并增强细节保真度。所提方法称为广义对抗求解器（GAS），在相似资源约束下表现优于现有求解器训练方法。代码已公开于 https://github.com/3145tttt/GAS。
原文摘要 · Abstract (English)
While diffusion models achieve state-of-the-art generation quality, they still suffer from computationally expensive sampling. Recent works address this issue with gradient-based optimization methods that distill a few-step ODE diffusion solver from the full sampling process, reducing the number of function evaluations from dozens to just a few. However, these approaches often rely on intricate training techniques and do not explicitly focus on preserving fine-grained details. In this paper, we introduce the Generalized Solver: a simple parameterization of the ODE sampler that does not require additional training tricks and improves quality over existing approaches. We further combine the original distillation loss with adversarial training, which mitigates artifacts and enhances detail fidelity. We call the resulting method the Generalized Adversarial Solver and demonstrate its superior performance compared to existing solver training methods under similar resource constraints. Code is available at https://github.com/3145tttt/GAS.
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。