INVE：交互式神经视频编辑
INVE: Interactive Neural Video Editing
AI总结：
本文提出实时交互式神经视频编辑方法 INVE，利用 hash-grids、双向图像-图集映射和向量化编辑，将学习与推理速度较 LNA 提升 5 倍，并支持更丰富的直接编辑操作。
摘要：
我们提出了交互式神经视频编辑（Interactive Neural Video Editing，INVE），这是一种实时视频编辑解决方案，能够通过将稀疏帧编辑一致地传播到整个视频片段来辅助视频编辑过程。我们的方法受到近期 Layered Neural Atlas（LNA，分层神经图集）工作的启发。然而，LNA 存在两个主要缺点：（1）该方法对于交互式编辑而言速度过慢；（2）它对某些编辑用例支持不足，包括直接帧编辑和刚性纹理跟踪。为应对这些挑战，我们利用并采用由 hash-grids 编码驱动的高效网络架构，以大幅提升处理速度。此外，我们学习图像与图集之间的双向函数，并引入向量化编辑，这些共同支持在图集和帧中直接实现种类更多的编辑。与 LNA 相比，我们的 INVE 将学习和推理时间缩短了 5 倍，并支持多种 LNA 无法实现的视频编辑操作。我们通过全面的定量和定性分析展示了 INVE 在交互式视频编辑方面相对于 LNA 的优越性，突出了其众多优势和改进的性能。有关视频结果，请参见 https://gabriel-huang.github.io/inve/。
英文摘要：
We present Interactive Neural Video Editing (INVE), a real-time video editing solution, which can assist the video editing process by consistently propagating sparse frame edits to the entire video clip. Our method is inspired by the recent work on Layered Neural Atlas (LNA). LNA, however, suffers from two major drawbacks: (1) the method is too slow for interactive editing, and (2) it offers insufficient support for some editing use cases, including direct frame editing and rigid texture tracking. To address these challenges we leverage and adopt highly efficient network architectures, powered by hash-grids encoding, to substantially improve processing speed. In addition, we learn bi-directional functions between image-atlas and introduce vectorized editing, which collectively enables a much greater variety of edits in both the atlas and the frames directly. Compared to LNA, our INVE reduces the learning and inference time by a factor of 5, and supports various video editing operations that LNA cannot. We showcase the superiority of INVE over LNA in interactive video editing through a comprehensive quantitative and qualitative analysis, highlighting its numerous advantages and improved performance. For video results, please see https://gabriel-huang.github.io/inve/
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。
