K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
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.
Code (2)
Tasks
DecoderNovel View SynthesisSimilar Papers 제목 키워드 기반
Learning Neural Implicit Surfaces with Object-Aware Radiance Fields
Recent progress on multi-view 3D object reconstruction has featured neural implicit surfaces via learning high-fidelity radiance fields. However, most approaches hinge on the visual hull derived from cost-expensive s…
3D Object ReconstructionObjectObject ReconstructionMERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale …
Neural Processing of Tri-Plane Hybrid Neural Fields
Driven by the appealing properties of neural fields for storing and communicating 3D data, the problem of directly processing them to address tasks such as classification and part segmentation has emerged and has been in…
Multi-Plane Neural Radiance Fields for Novel View Synthesis
Novel view synthesis is a long-standing problem that revolves around rendering frames of scenes from novel camera viewpoints. Volumetric approaches provide a solution for modeling occlusions through the explicit 3D repre…
NeRFNovel View SynthesisMuRF: Multi-Baseline Radiance Fields
We present Multi-Baseline Radiance Fields (MuRF), a general feed-forward approach to solving sparse view synthesis under multiple different baseline settings (small and large baselines, and different number of input view…
NeRFZero-shot Generalization