· 2023
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
- 476citations
- 2023year
Short summary
K-Planes, a new white-box model, represents 4D scenes (space + time) using planes, enabling 1000x compression and state-of-the-art reconstruction fidelity with fast optimization.
AI-generated from the title and abstract; the full text is not read.
Key points
- K-Planes models d-dimensional radiance fields using planes, enabling representation of both static (3D) and dynamic (4D) scenes.
- The planar factorization allows easy integration of dimension-specific priors, such as temporal smoothness.
- Achieves 1000x compression compared to a full 4D grid while maintaining competitive reconstruction fidelity.
- Uses a linear feature decoder with a learned color basis, matching performance of nonlinear MLPs.
AI-generated from the title and abstract; the full text is not read.
Abstract
We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions. Our model uses 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 recon- struction 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 sarafridov.github.io/K-Planes.
The authors' abstract, as published at the source., 2023 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Graphics and Computer-Aided Design
Computer Graphics and Computer-Aided DesignComputer Science