K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
This work addresses the challenge of efficiently representing and reconstructing dynamic radiance fields for computer vision and graphics applications, offering an incremental improvement with a more interpretable and memory-efficient approach.
The authors tackled the problem of modeling radiance fields for static and dynamic scenes by introducing k-planes, a white-box model that uses planar factorization to represent scenes in arbitrary dimensions, achieving competitive or state-of-the-art reconstruction fidelity with low memory usage, such as 1000x compression over a full 4D grid.
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 https://sarafridov.github.io/K-Planes.