TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenes

TL;DR

This paper introduces TK-Planes, an extension of K-Planes NeRF that uses tiered high-dimensional feature vectors to improve scene modeling and rendering in dynamic UAV-based scenes, effectively handling static and moving objects.

Contribution

The paper proposes a novel tiered feature vector approach for NeRF, enhancing dynamic scene modeling and rendering accuracy in UAV applications.

Findings

Significant accuracy improvements over existing neural rendering methods.

Effective modeling of both static and dynamic scene components.

Robust performance on challenging UAV datasets.

Abstract

In this paper, we present a new approach to bridge the domain gap between synthetic and real-world data for unmanned aerial vehicle (UAV)-based perception. Our formulation is designed for dynamic scenes, consisting of small moving objects or human actions. We propose an extension of K-Planes Neural Radiance Field (NeRF), wherein our algorithm stores a set of tiered feature vectors. The tiered feature vectors are generated to effectively model conceptual information about a scene as well as an image decoder that transforms output feature maps into RGB images. Our technique leverages the information amongst both static and dynamic objects within a scene and is able to capture salient scene attributes of high altitude videos. We evaluate its performance on challenging datasets, including Okutama Action and UG2, and observe considerable improvement in accuracy over state of the art neural rendering methods.