3.4 3D-Aware

P243

ID	Year	Name	Note	Tags	Link
	2023	Layered Neural Atlases for Consistent Video Editing	- Decompose a video into a foreground image + a background image - Edit the foreground/background image = edit the video ✅ 对背景进行编辑（图片编辑、风格迁移）再传播到不同帧上去。
	2023	VidEdit: Zero-Shot and Spagally Aware Text-Driven Video Edigng	Atlas-based video editing - Decompose a video into a foreground image + a background image - Edit the foreground/background image = edit the video - Use diffusion to edit foreground/background atlas > ✅ 前景编辑： (1) 抠出第一帧前景并进行编辑得到 Partial Atlas. ✅ (2) Partial Atlas 作为下一帧的 condition 整体上是自回归的。 ✅ 所有 Partial 合起来得到一个整体。 ✅ 背景使用深度信息作为 cordition.
	2023	Shape-aware Text-driven Layered Video Editing	Atlas-based video editing
	2023.11	Stablevideo: Text-driven consistency-aware diffusion video editing	✅ 给一个场景的多视角图片，基于 MLP 学习 3D 场景的隐式表达。
115	2023	CoDeF: Content Deformation Fields for Temporally Consistent Video Processing			link
	2023	HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video
116	2023	DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing			link

本文出自CaterpillarStudyGroup，转载请注明出处。

https://caterpillarstudygroup.github.io/ImportantArticles/