HyperPlanes：用于快速NeRF适配的超网络方法
HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation
AI总结：
针对NeRF泛化性差、单物体训练算力成本高的问题，提出基于超网络的小样本学习方法HyperPlanes，推理无需梯度优化，可单步生成高质量3D表征，性能经SOTA对比和消融研究验证。
摘要：
神经辐射场（NeRF）是从少量基础图像合成3D物体新视图的公认标准方法。然而，NeRF的泛化性能有限，这意味着我们需要耗费大量计算资源为每个待表征物体训练独立架构。为解决该问题，我们提出一种基于超网络范式的小样本学习方法，推理过程无需梯度优化。该超网络从训练数据中收集信息，并生成通用权重的更新值。由此，我们开发出一种高效方法，可仅通过少量图像单步生成高质量3D物体表征。这一结论已通过与当前最优（SOTA）方案的直接对比及全面消融研究得到验证。
英文摘要：
Neural radiance fields (NeRFs) are a widely accepted standard for synthesizing new 3D object views from a small number of base images. However, NeRFs have limited generalization properties, which means that we need to use significant computational resources to train individual architectures for each item we want to represent. To address this issue, we propose a few-shot learning approach based on the hypernetwork paradigm that does not require gradient optimization during inference. The hypernetwork gathers information from the training data and generates an update for universal weights. As a result, we have developed an efficient method for generating a high-quality 3D object representation from a small number of images in a single step. This has been confirmed by direct comparison with the state-of-the-art solutions and a comprehensive ablation study.
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。
