arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.04041cs.CVcs.RO
收藏

ParticleNeRF:一种基于粒子的在线神经辐射场编码

ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fields

Queensland University of Technology(昆士兰科技大学);University of Adelaide(阿德莱德大学)

Jad Abou-Chakra, Feras Dayoub, Niko Sünderhauf

摘要:

虽然现有的动态场景的神经辐射场(NeRFs)是离线方法,重点是视觉保真度,但我们的论文解决了优先考虑实时适应性的在线用例。我们提出了ParticleNeRF,这是一种新的方法,通过每200毫秒在线学习最新的表示来动态适应场景几何形状的变化。ParticleNeRF使用一种新的基于粒子的参数编码来实现这一点。我们将特征耦合到空间中的粒子,并将光度重建损失反向传播到粒子的位置梯度中,然后将其解释为速度矢量。由一个轻量级的物理系统来处理碰撞,这使得功能可以随着场景几何体的变化而自由移动。我们演示ParticleNeRF在各种动态场景中包含平移,旋转,铰接和可变形的对象。ParticleNeRF是第一个在线动态NeRF,实现了快速适应性,比暴力在线InstantNGP和其他在线约束动态场景的基线方法具有更好的视觉保真度。您可以在我们的项目网站https://sites.google.com/view/particlenerf上找到我们系统的视频。

英文摘要:

While existing Neural Radiance Fields (NeRFs) for dynamic scenes are offline methods with an emphasis on visual fidelity, our paper addresses the online use case that prioritises real-time adaptability. We present ParticleNeRF, a new approach that dynamically adapts to changes in the scene geometry by learning an up-to-date representation online, every 200ms. ParticleNeRF achieves this using a novel particle-based parametric encoding. We couple features to particles in space and backpropagate the photometric reconstruction loss into the particles' position gradients, which are then interpreted as velocity vectors. Governed by a lightweight physics system to handle collisions, this lets the features move freely with the changing scene geometry. We demonstrate ParticleNeRF on various dynamic scenes containing translating, rotating, articulated, and deformable objects. ParticleNeRF is the first online dynamic NeRF and achieves fast adaptability with better visual fidelity than brute-force online InstantNGP and other baseline approaches on dynamic scenes with online constraints. Videos of our system can be found at our project website https://sites.google.com/view/particlenerf.

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。

↑