神經編輯器：通過操作點雲編輯神經輻射場

摘要

本文提出了一種名為神經編輯器（NeuralEditor）的方法，使神經輻射場（NeRFs）能夠原生地進行一般形狀編輯任務。儘管在新視角合成方面取得了令人印象深刻的成果，但對於 NeRFs 來說，編輯場景的形狀仍然是一個基本挑戰。我們的關鍵洞察是利用明確的點雲表示作為構建 NeRFs 的基礎結構，靈感來自於對 NeRF 渲染的直觀解釋，即將相關的 3D 點雲投影或“繪製”到 2D 圖像平面的過程。為此，神經編輯器引入了一種基於 K-D 樹引導的密度自適應體素內的確定積分的新型渲染方案，通過優化實現了高質量的渲染結果和精確的點雲。神經編輯器通過在點雲之間映射相關點來執行形狀編輯。廣泛的評估表明，神經編輯器在形狀變形和場景變形任務中實現了最先進的性能。值得注意的是，神經編輯器支持零樣本推斷以及對編輯後場景進行進一步微調。我們的代碼、基準測試和演示視頻可在 https://immortalco.github.io/NeuralEditor 找到。

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.

神經編輯器：通過操作點雲編輯神經輻射場

NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds

摘要

Support