Hierarchical Scoring with 3D Gaussian Splatting for Instance Image-Goal Navigation

TL;DR

This paper introduces a hierarchical scoring framework for instance image-goal navigation that efficiently identifies optimal viewpoints using semantic and geometric cues, improving performance and reducing redundancy in view sampling.

Contribution

The paper presents a novel hierarchical scoring method combining semantic and geometric cues for better viewpoint selection in IIN, leveraging 3D Gaussian splatting and CLIP.

Findings

Achieves state-of-the-art results on simulated benchmarks

Demonstrates effective real-world applicability

Reduces redundancy in view sampling

Abstract

Instance Image-Goal Navigation (IIN) requires autonomous agents to identify and navigate to a target object or location depicted in a reference image captured from any viewpoint. While recent methods leverage powerful novel view synthesis (NVS) techniques, such as three-dimensional Gaussian splatting (3DGS), they typically rely on randomly sampling multiple viewpoints or trajectories to ensure comprehensive coverage of discriminative visual cues. This approach, however, creates significant redundancy through overlapping image samples and lacks principled view selection, substantially increasing both rendering and comparison overhead. In this paper, we introduce a novel IIN framework with a hierarchical scoring paradigm that estimates optimal viewpoints for target matching. Our approach integrates cross-level semantic scoring, utilizing CLIP-derived relevancy fields to identify regions with high semantic similarity to the target object class, with fine-grained local geometric scoring that performs precise pose estimation within promising regions. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on simulated IIN benchmarks and real-world applicability.