Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation

TL;DR

Context-Nav introduces a geometry-grounded, viewpoint-aware 3D spatial reasoning approach for text-goal instance navigation, improving exploration and disambiguation without task-specific training.

Contribution

It presents a novel framework that combines global exploration guided by dense text-image alignments with 3D spatial verification, achieving state-of-the-art results without training.

Findings

State-of-the-art performance on InstanceNav and CoIN-Bench datasets.

Encoding full captions into the value map improves exploration efficiency.

Viewpoint-aware 3D verification reduces incorrect stopping in navigation.

Abstract

Text-goal instance navigation (TGIN) asks an agent to resolve a single, free-form description into actions that reach the correct object instance among same-category distractors. We present \textit{Context-Nav}, which elevates long, contextual captions from a local matching cue to a global exploration prior and verifies candidates through 3D spatial reasoning. First, we compute dense text-image alignments for a value map that ranks frontiers -- guiding exploration toward regions consistent with the entire description rather than early detections. Second, upon observing a candidate, we perform a viewpoint-aware relation check: the agent samples plausible observer poses, aligns local frames, and accepts a target only if the spatial relations can be satisfied from at least one viewpoint. The pipeline requires no task-specific training or fine-tuning; we attain state-of-the-art performance on InstanceNav and CoIN-Bench. Ablations show that (i) encoding full captions into the value map avoids wasted motion and (ii) explicit, viewpoint-aware 3D verification prevents semantically plausible but incorrect stops. This suggests that geometry-grounded spatial reasoning is a scalable alternative to heavy policy training or human-in-the-loop interaction for fine-grained instance disambiguation in cluttered 3D scenes.