3. Dynamic Image-Based Rendering 给定一个具有帧的动态场景的单目视频(I1, I2,…,, IN ) 和已知的相机参数 (P1, P2,., PN ),目标是在视频中任何所需时间合成一个新的视点。与许多其他方法一样,此方法训练每个视频,首先优化模型来重建输入帧,然后使用该模型渲染新视图。 不像最近的动态NeRF方法那样直接...
Google开发了一种新的动态图片渲染方法DynIBaR（Neural Dynamic Image-Based Rendering），只要使用单一视频，就可以生成复杂且动态的场景，并以真实自由摄影机视点渲染出新画面，实现诸如子弹时间、摄影防手震、慢动作甚至是散景（Bokeh）等特效。由于NeRF（Neural Radiance Fields）技术的发展，开发者能够重建和渲染静态3D...
Writers: Zhengqi Li, Qianqian Wang, Forrester Cole, Richard Tucker, Noah Snavely PDF:DynIBaR: Neural Dynamic Image-Based Rendering Abstract We address the problem of synthesizing novel views from a monocular video depicting a complex dynamic scene. State-of-the-art methods based on temporally vary...
@InProceedings{Li_2023_CVPR, author = {Li, Zhengqi and Wang, Qianqian and Cole, Forrester and Tucker, Richard and Snavely, Noah}, title = {DynIBaR: Neural Dynamic Image-Based Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}...