用强化学习自动优化3D渲染采样，提速近一半且画质不降。
SAC-NeRF: Adaptive Ray Sampling for Neural Radiance Fields via Soft Actor-Critic Reinforcement Learning
- 通过强化学习动态决定每条光线该采多少点。
- 采样点减少35%-48%，画质仅比全采样低0.3-0.8 dB PSNR。
- 适合追求高效渲染的3D重建与视觉生成研究者。
神经辐射场（NeRF）虽能实现逼真新视角合成，但体积渲染中密集采样导致计算效率低下。本文提出SAC-NeRF，一种基于软演员-评论家（SAC）强化学习的自适应采样框架。将采样过程建模为马尔可夫决策过程，让智能体根据场景特征学习采样策略。引入三项技术：(1) 高斯混合分布颜色模型提供不确定性估计；(2) 多组件奖励函数平衡质量、效率与一致性；(3) 两阶段训练策略应对环境非平稳性问题。在Synthetic-NeRF和LLFF数据集上的实验表明，SAC-NeRF可减少35%-48%采样点，同时保持渲染质量在密集采样基线的0.3-0.8 dB PSNR范围内。尽管学习策略具有场景特异性且强化学习框架较复杂，但本工作证明数据驱动采样能发现人工难以设计的有效模式。
原文摘要 · Abstract (English)
Neural Radiance Fields (NeRF) have achieved photorealistic novel view synthesis but suffer from computational inefficiency due to dense ray sampling during volume rendering. We propose SAC-NeRF, a reinforcement learning framework that learns adaptive sampling policies using Soft Actor-Critic (SAC). Our method formulates sampling as a Markov Decision Process where an RL agent learns to allocate samples based on scene characteristics. We introduce three technical components: (1) a Gaussian mixture distribution color model providing uncertainty estimates, (2) a multi-component reward function balancing quality, efficiency, and consistency, and (3) a two-stage training strategy addressing environment non-stationarity. Experiments on Synthetic-NeRF and LLFF datasets show that SAC-NeRF reduces sampling points by 35-48\% while maintaining rendering quality within 0.3-0.8 dB PSNR of dense sampling baselines. While the learned policy is scene-specific and the RL framework adds complexity compared to simpler heuristics, our work demonstrates that data-driven sampling strategies can discover effective patterns that would be difficult to hand-design.
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。