Block-NeRF: Scalable Large Scene Neural View Synthesis
Block-NeRF: Scalable Large Scene Neural View Synthesis
复制标题
DOI：
10.1109/cvpr52688.2022.00807
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Matthew Tancik;Vincent Casser;Xinchen Yan;Sabeek Pradhan;B. Mildenhall;Pratul P. Srinivasan;J. Barron;Henrik Kretzschmar
中科院分区：
文献类型：
--
作者：
Matthew Tancik;Vincent Casser;Xinchen Yan;Sabeek Pradhan;B. Mildenhall;Pratul P. Srinivasan;J. Barron;Henrik Kretzschmar
我们提出了块神经网络，它是神经辐射场的一种变体，可以表示大规模的环境。具体地说，我们演示了当缩放NERF以渲染跨越多个块的城市规模的场景时，将场景分解为单独训练的NERF是至关重要的。这种分解将渲染时间与场景大小分离，使渲染能够缩放到任意大的环境，并允许按块更新环境。我们采用了几项架构更改，使NERF对在不同环境条件下几个月捕获的数据具有健壮性。我们为每个单独的NERF添加了外观嵌入、学习的姿势优化和可控曝光，并引入了一个在相邻NERF之间对齐外观的过程，以便它们可以无缝组合。我们从280万张图像中构建了一个Block-nerf网格，以创建迄今为止最大的神经场景表示，能够渲染整个旧金山社区。
We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments. Specifically, we demonstrate that when scaling NeRF to render city-scale scenes spanning multiple blocks, it is vital to de-compose the scene into individually trained NeRFs. This decomposition decouples rendering time from scene size, enables rendering to scale to arbitrarily large environments, and allows per-block updates of the environment. We adopt several architectural changes to make NeRF robust to data captured over months under different environmental conditions. We add appearance embeddings, learned pose refinement, and controllable exposure to each individual NeRF, and introduce a procedure for aligning appearance between adjacent NeRFs so that they can be seamlessly combined. We build a grid of Block-NeRFs from 2.8 million images to create the largest neural scene representation to date, capable of rendering an entire neighborhood of San Francisco.