雕刻NeRF几何：基于人类偏好的3D感知人脸GAN微调
Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN
AI总结：
提出直接对辐射场密度值进行人类偏好强化学习微调，无需网格或形状先验，显著改善3D人脸几何，在74.4%的成对比较中用户偏好微调后的几何。
摘要：
基于人类反馈的强化学习（RLHF）用于3D生成已在多项工作中得到应用，但大多数现有流程优化显式表面表示，通常通过将辐射场转换为网格并在大量表面监督数据上训练。我们则直接对预训练的3D感知生成模型进行微调，基于辐射场密度（$\sigma$）值的学习奖励，无需外部提供的网格或形状先验。奖励模型无需预训练，易于在小规模偏好样本上训练，并带来3D几何的稳健改进。针对无条件的3D感知人脸GAN（EG3D），我们的奖励直接读取神经辐射场（NeRF）的连续3D密度场，仅提供几何学习信号，无需文本条件、网格提取或多视角渲染。密度一致性约束在几何重塑时保持2D外观质量相似，但带来可测量且有限的分布代价（FID-50k从4.09升至6.66）：作为概念验证，微调后的生成器基于单个标注者的偏好进行训练，在74.4%的成对比较中用户更偏好其生成的人脸几何。
英文摘要：
Reinforcement learning from human feedback (RLHF) for 3D generation is now established across a number of works, but most existing pipelines optimise explicit surface representations, often by converting radiance fields into meshes and training heavily on surface-supervised data. We instead fine-tune a pretrained 3D-aware generative model directly from a learned reward over radiance-field density ($σ$) values, with no externally supplied mesh or shape prior. The reward model requires no pretraining, trains easily on a small set of preference samples, and yields robust improvement in 3D geometry. Working on an unconditional 3D-aware face GAN (EG3D), our reward reads the continuous 3D density field of the neural radiance field (NeRF) directly and supplies a geometry-only learning signal, requiring neither text conditioning, mesh extraction, nor multi-view rendering. A density-consistency constraint keeps the 2D appearance qualitatively similar while the geometry is reshaped, at a measurable but bounded distributional cost (FID-50k rises from 4.09 to 6.66): the fine-tuned generator, trained from the preferences of a single annotator as a proof of concept, produces face geometries preferred by users in 74.4% of pairwise comparisons.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
