Hi-Map: Hierarchical Factorized Radiance Field for High-Fidelity Monocular Dense Mapping

TL;DR

Hi-Map is a novel neural radiance field approach that achieves high-fidelity monocular dense mapping efficiently by using a hierarchical, factorized scene representation without external depth priors.

Contribution

The paper introduces a hierarchical factorized scene representation and a dual-path encoding strategy for improved monocular dense mapping with NeRF, eliminating the need for external depth priors.

Findings

Outperforms state-of-the-art NeRF-based monocular mapping methods in accuracy.

Achieves efficient and high-fidelity scene reconstruction from only RGB inputs.

Demonstrates robustness in textureless and distant regions.

Abstract

In this paper, we introduce Hi-Map, a novel monocular dense mapping approach based on Neural Radiance Field (NeRF). Hi-Map is exceptional in its capacity to achieve efficient and high-fidelity mapping using only posed RGB inputs. Our method eliminates the need for external depth priors derived from e.g., a depth estimation model. Our key idea is to represent the scene as a hierarchical feature grid that encodes the radiance and then factorizes it into feature planes and vectors. As such, the scene representation becomes simpler and more generalizable for fast and smooth convergence on new observations. This allows for efficient computation while alleviating noise patterns by reducing the complexity of the scene representation. Buttressed by the hierarchical factorized representation, we leverage the Sign Distance Field (SDF) as a proxy of rendering for inferring the volume density, demonstrating high mapping fidelity. Moreover, we introduce a dual-path encoding strategy to strengthen the photometric cues and further boost the mapping quality, especially for the distant and textureless regions. Extensive experiments demonstrate our method's superiority in geometric and textural accuracy over the state-of-the-art NeRF-based monocular mapping methods.