# AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation

arXiv: https://arxiv.org/abs/2604.05351 · HTML: https://mlsanity.com/paper/2604.05351/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [Semi-parametric Topological Memory for Navigation](https://mlsanity.com/paper/1803.00653/) (2018)
- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [TTT3R: 3D Reconstruction as Test-Time Training](https://mlsanity.com/paper/2509.26645/) (2025)
- [STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer](https://mlsanity.com/paper/2508.10893/) (2025)
- [OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav](https://mlsanity.com/paper/2303.07798/) (2023)
- [InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams](https://mlsanity.com/paper/2601.02281/) (2026)
- [Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances](https://mlsanity.com/paper/2211.15876/) (2022)
- [Emergent Outlier View Rejection in Visual Geometry Grounded Transformers](https://mlsanity.com/paper/2512.04012/) (2025)
- [Hierarchical Scoring with 3D Gaussian Splatting for Instance Image-Goal Navigation](https://mlsanity.com/paper/2506.07338/) (2025)
- [SplatSearch: Instance Image Goal Navigation for Mobile Robots using 3D Gaussian Splatting and Diffusion Models](https://mlsanity.com/paper/2511.12972/) (2025)

## Built on by (most cited first, 2 of 2)

- [From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation](https://mlsanity.com/paper/2607.03792/) (2026)
- [G2WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation](https://mlsanity.com/paper/2610.16558/) (2026)

## Abstract (arXiv)

Image Goal Navigation (ImageNav) is evaluated by a coarse success criterion, the agent must stop within 1m of the target, which is sufficient for finding objects but falls short for downstream tasks such as grasping that require precise positioning. We introduce AnyImageNav, a training-free system that pushes ImageNav toward this more demanding setting. Our key insight is that the goal image can be treated as a geometric query: any photo of an object, a hallway, or a room corner can be registered to the agent's observations via dense pixel-level correspondences, enabling recovery of the exact 6-DoF camera pose. Our method realizes this through a semantic-to-geometric cascade: a semantic relevance signal guides exploration and acts as a proximity gate, invoking a 3D multi-view foundation model only when the current view is highly relevant to the goal image; the model then self-certifies its registration in a loop for an accurate recovered pose. Our method sets state-of-the-art navigation success rates on Gibson (93.1%) and HM3D (82.6%), and achieves pose recovery that prior methods do not provide: a position error of 0.27m and heading error of 3.41 degrees on Gibson, and 0.21m / 1.23 degrees on HM3D, a 5-10x improvement over adapted baselines.Our project page: https://yijie21.github.io/ain/