Hierarchical Scoring with 3D Gaussian Splatting for Instance Image-Goal Navigation
This work addresses the challenge of efficient and accurate navigation for autonomous agents by improving view selection, representing an incremental advance over existing methods.
The paper tackles the problem of Instance Image-Goal Navigation by introducing a hierarchical scoring framework that estimates optimal viewpoints for target matching, reducing redundancy and overhead compared to random sampling methods. It achieves state-of-the-art performance on simulated benchmarks, demonstrating real-world applicability.
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.