SeamlessNeRF：利用梯度传播拼接局部 NeRF
SeamlessNeRF: Stitching Part NeRFs with Gradient Propagation
AI总结：
本文提出 SeamlessNeRF，通过固定边界颜色并保持目标梯度的优化方法，首次将梯度引导的外观编辑引入辐射场，实现多个 NeRF 的无缝外观融合与拼接。
摘要：
神经辐射场（NeRFs）已成为三维物体和场景的有前景的数字媒介，激发了该领域扩展编辑能力的研究热潮。在多个 NeRF 之间进行无缝编辑与合并的任务，类似于二维图像编辑中的“泊松融合”，仍然是一项关键操作，但现有工作对此探索不足。为填补这一空白，我们提出了 SeamlessNeRF，这是一种用于多个 NeRF 无缝外观融合的新方法。具体而言，我们旨在优化目标辐射场的外观，以使其与源场的合并达到和谐。我们提出了一种精心设计的融合优化流程，该流程受以下约束：1）在源场与目标场之间的相交边界区域固定辐射颜色；2）保持目标的原始梯度。大量实验验证了我们的方法能够通过梯度有效地将源外观从边界区域传播到整个目标场。据我们所知，SeamlessNeRF 是首个将梯度引导的外观编辑引入辐射场的工作，为以 NeRF 表示的三维物体的无缝拼接提供了解决方案。
英文摘要：
Neural Radiance Fields (NeRFs) have emerged as promising digital mediums of 3D objects and scenes, sparking a surge in research to extend the editing capabilities in this domain. The task of seamless editing and merging of multiple NeRFs, resembling the ``Poisson blending'' in 2D image editing, remains a critical operation that is under-explored by existing work. To fill this gap, we propose SeamlessNeRF, a novel approach for seamless appearance blending of multiple NeRFs. In specific, we aim to optimize the appearance of a target radiance field in order to harmonize its merge with a source field. We propose a well-tailored optimization procedure for blending, which is constrained by 1) pinning the radiance color in the intersecting boundary area between the source and target fields and 2) maintaining the original gradient of the target. Extensive experiments validate that our approach can effectively propagate the source appearance from the boundary area to the entire target field through the gradients. To the best of our knowledge, SeamlessNeRF is the first work that introduces gradient-guided appearance editing to radiance fields, offering solutions for seamless stitching of 3D objects represented in NeRFs.
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。
