Abstract
We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions. Our model uses d choose 2 planes to represent a d-dimensional scene, providing a seamless way to go from static (d=3) to dynamic (d=4) scenes. This planar factorization makes adding dimension-specific priors easy, e.g. temporal smoothness and multi-resolution spatial structure, and induces a natural decomposition of static and dynamic components of a scene. We use a linear feature decoder with a learned color basis that yields similar performance as a nonlinear black-box MLP decoder. Across a range of synthetic and real, static and dynamic, fixed and varying appearance scenes, k-planes yields competitive and often state-of-the-art reconstruction fidelity with low memory usage, achieving 1000x compression over a full 4D grid, and fast optimization with a pure PyTorch implementation. For video results and code, please see this http URL.
Abstract (translated)
我们引入了k-平面,一个任意维度光照场的白盒模型。我们的模型使用d选择2平面来代表d-dimensional场景,提供了从静态(d=3)到动态(d=4)场景的无缝过渡。这种平面组合使得添加维度特定的前置变得容易,例如时间平滑和多分辨率空间结构,并诱导了场景静态和动态组件的自然分解。我们使用一种线性特征解码器和 learnable 颜色基,使其性能与非线性黑盒MLP解码器相似。在模拟和真实、静态和动态、固定和不断变化的外观场景范围内,k-平面提供了竞争且往往最先进的重构精度,同时使用低内存占用实现满4D网格的1000倍压缩,并使用纯PyTorch实现快速优化。如需视频结果和代码,请访问此httpURL。
URL
https://arxiv.org/abs/2301.10241