Skip to content
Open access

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

Jun 2025 · IEEE Robotics and Automation Letters · Vol 11, pp. 11307-11313 · 4 citations · ⚡ 1 influential · 38 references
Computer Science

TL;DR

The framework, GauScoreMap, performs hierarchical scoring: a training-free global stage produces a CLIP relevance field over Gaussians and prunes the scene to a small set of candidate regions, and a local stage performs ray-image cross-attention within those regions and triangulates the 6D camera pose from the top-scoring rays.

Abstract

Instance Image-Goal Navigation (IIN) asks an agent to locate the specific object instance shown in a goal image. Existing 3D Gaussian Splatting (3DGS) based methods rely on pose-centric search—sampling many viewpoints, rendering them, and comparing against the goal—which is inefficient in continuous 6-DoF space. We instead treat the 3DGS scene as a joint semantic-geometric ray field and reformulate localization as inference over this field. Our framework, GauScoreMap, performs hierarchical scoring: a training-free global stage produces a CLIP relevance field over Gaussians and prunes the scene to a small set of candidate regions, and a local stage performs ray-image cross-attention within those regions and triangulates the 6D camera pose from the top-scoring rays. On the HM3D IIN benchmark, GauScoreMap sets a new state of the art with more than an order of magnitude lower per-query latency than the prior 3DGS-based work, and we validate the pipeline in a real-world environment.

Read PDF

Similar papers

#artificial intelligence Preprint Sep 2026

SceneBench: A Hierarchical Benchmark for Vision-Language Understanding of 3D Scenes

SceneBench is introduced, a benchmark of 966 photorealistic 3D scenes reconstructed with Gaussian Splatting and densely annotated with hierarchical semantics spanning scenes, rooms, functional areas, object groups, and individual objects that provides a realistic testbed for developing and evaluating models capable of...

Anubhav Khanal, Prabigya Acharya, Roshni Poudel et al. · 0 citations
Review Open access Aug 2026

Semantic 3D Gaussian Splatting: A State-of-the-Art Review

A unified multi-axis taxonomy is introduced that enables us to classify the available methods in 3D Gaussian splatting methods in terms of five complementary categories: semantic vocabulary space, representation form, functional role, knowledge source, and query mechanism.

J. Flotyński · 0 citations
Preprint Sep 2026

PGL-3D: Towards Progressive Geometric Learning for 3D Visual Query Localization

3D Visual Query Localization (3DVQL) retrieves the latest contiguous occurrence of a queried object in an RGB--point-cloud sequence and predicts a 9-DoF cuboid for every response frame. The query is captured independently of the search sequence, so its annotated pose may differ from how the object appears in the search...

Liang Peng, Shi-Zhuo Mu, Bo-Han Tan et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking

This work introduces PLANET, an end-to-end multi-object tracker designed to move beyond the image plane, and lifts existing 2D tracking datasets into 3D by embedding reconstructed 3D scene geometry into the features and positional encodings used during query formation.

Orcun Cetintas, Guillem Brasó, Tim Meinhardt et al. · 0 citations
Open access Sep 2026

Semantic-Guided Adaptive Gaussian Segmentation

3D Gaussian Splatting (3DGS) enables real-time photorealistic scene reconstruction, yet its segmentation tasks suffer from two critical flaws: poor 3D consistency (e.g., blurred instance boundaries and unstable cross-view semantic association) and insufficient structural awareness near ambiguous object boundaries. To a...

Ying-Han Zhou, Fan Zhou · 0 citations
Preprint Sep 2026

DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussians

Recent advances in 3D Gaussian Splatting have enabled open-vocabulary and referring segmentation by distilling semantic knowledge from 2D foundation models into 3D representations. However, existing referring fields embed language features in a globally view-invariant space, making them fundamentally unable to resolve...

Thanh-Khoi Nguyen, Thien-Phuc Tran, Minh-Triet Tran · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.