DualNeRF：基于双场表示的文字驱动三维场景编辑
DualNeRF: Text-Driven 3D Scene Editing via Dual-Field Representation
AI总结：
DualNeRF提出双场表示与模拟退火策略，解决IN2N在文字驱动三维场景编辑中的背景模糊和局部最优问题，并利用CLIP指标提升编辑质量。
摘要：
近年来，去噪扩散模型在二维图像生成和编辑方面取得了令人瞩目的成果。Instruct-NeRF2NeRF（IN2N）通过“迭代数据集更新”（IDU）策略将扩散模型的成功引入三维场景编辑。尽管取得了令人印象深刻的结果，IN2N仍存在背景模糊和陷入局部最优的问题。第一个问题源于IN2N缺乏对背景保持的有效引导，而第二个问题则源于IDU过程中图像编辑与NeRF训练之间的相互作用。在本工作中，我们提出DualNeRF来解决这些问题。我们提出一种双场表示来保留原始场景的特征，并在IDU期间将其作为额外的引导提供给模型以保持背景。此外，我们将模拟退火策略嵌入IDU中，使我们的模型具备解决局部最优问题的能力。我们还使用基于CLIP的一致性指标，通过过滤低质量编辑来进一步提高编辑质量。大量实验表明，我们的方法在定性和定量两方面均优于以往方法。
英文摘要：
Recently, denoising diffusion models have achieved promising results in 2D image generation and editing. Instruct-NeRF2NeRF (IN2N) introduces the success of diffusion into 3D scene editing through an "Iterative dataset update" (IDU) strategy. Though achieving fascinating results, IN2N suffers from problems of blurry backgrounds and trapping in local optima. The first problem is caused by IN2N's lack of efficient guidance for background maintenance, while the second stems from the interaction between image editing and NeRF training during IDU. In this work, we introduce DualNeRF to deal with these problems. We propose a dual-field representation to preserve features of the original scene and utilize them as additional guidance to the model for background maintenance during IDU. Moreover, a simulated annealing strategy is embedded into IDU to endow our model with the power of addressing local optima issues. A CLIP-based consistency indicator is used to further improve the editing quality by filtering out low-quality edits. Extensive experiments demonstrate that our method outperforms previous methods both qualitatively and quantitatively.
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。
