NeRF acquisition typically requires careful choice of near planes for the different cameras or suffers from background collapse, creating floating artifacts on the edges of the captured scene. The key insight of this work is that background collapse is caused by a higher density of samples in regions near cameras. As a result of this sampling bias, near-camera volumes receive significantly more gradients, leading to incorrect density buildup. We propose a gradient scaling approach to counter-balance this bias, removing the need for near planes, while preventing background collapse. Our method can be implemented in a few lines, does not induce any significant overhead, and is compatible with most NeRF implementations.

翻译：NeRF采集通常需要为不同相机仔细选择近平面，否则会出现背景坍塌的问题，在捕获场景边缘产生浮动伪影。本工作的关键发现是，背景坍塌源于相机附近区域具有更高的采样密度。由于这种采样偏差，近相机体素接收到的梯度显著增多，导致不正确的密度积累。我们提出了一种梯度缩放方法，以抵消这种偏差，在消除近平面需求的同时防止背景坍塌。该方法仅需数行代码即可实现，不会引入显著计算开销，且兼容大多数NeRF实现。