神经编辑器：通过操纵点云编辑神经辐射场

摘要

本文提出了神经编辑器 NeuralEditor，可使神经辐射场（NeRFs）在一般形状编辑任务中本地可编辑。尽管在新视角合成方面取得了令人印象深刻的成果，但对于 NeRFs 来说，编辑场景形状仍然是一个基本挑战。我们的关键见解是利用显式点云表示作为构建 NeRFs 的基础结构，受 NeRF 渲染的直观解释启发，即将相关的 3D 点云投影或“绘制”到 2D 图像平面的过程。为此，NeuralEditor 提出了一种基于 K-D 树引导的密度自适应体素内确定性积分的新型渲染方案，通过优化实现了高质量的渲染结果和精确的点云。然后，NeuralEditor 通过映射点云之间的相关点执行形状编辑。广泛的评估表明，NeuralEditor 在形状变形和场景变形任务中实现了最先进的性能。值得注意的是，NeuralEditor 支持零次推断和对编辑后场景的进一步微调。我们的代码、基准测试和演示视频可在 https://immortalco.github.io/NeuralEditor 获取。

English

This paper proposes NeuralEditor that enables neural radiance fields (NeRFs) natively editable for general shape editing tasks. Despite their impressive results on novel-view synthesis, it remains a fundamental challenge for NeRFs to edit the shape of the scene. Our key insight is to exploit the explicit point cloud representation as the underlying structure to construct NeRFs, inspired by the intuitive interpretation of NeRF rendering as a process that projects or "plots" the associated 3D point cloud to a 2D image plane. To this end, NeuralEditor introduces a novel rendering scheme based on deterministic integration within K-D tree-guided density-adaptive voxels, which produces both high-quality rendering results and precise point clouds through optimization. NeuralEditor then performs shape editing via mapping associated points between point clouds. Extensive evaluation shows that NeuralEditor achieves state-of-the-art performance in both shape deformation and scene morphing tasks. Notably, NeuralEditor supports both zero-shot inference and further fine-tuning over the edited scene. Our code, benchmark, and demo video are available at https://immortalco.github.io/NeuralEditor.

神经编辑器：通过操纵点云编辑神经辐射场

NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds

摘要

Support