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

• URL: http://arxiv.org/abs/2604.05351v3
• Date: Thu, 09 Apr 2026 02:21:57 GMT
• Title: AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation
• Abstract summary: We introduce AnyImageNav, a training-free system that pushes ImageNav toward a more demanding setting.<n>Our key insight is that the goal image can be treated as a geometric query.<n>Our method sets state-of-the-art navigation success rates on Gibson (93.1%) and HM3D (82.6%)
• Score: 10.175661009911257
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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/

Related papers

• DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching [0.5176742519438303]
  We propose a novel framework for single-shot shape and pose estimation of unknown spacecraft objects.<n>We first reconstruct a 3D shape model of the target, then estimate the relative six-degrees-of-freedom pose by learning dense 2D-3D correspondences.<n>Results show reliable pose estimates achieving 0.157 degrees mean pointing error using only a single image.
  arXiv  Detail & Related papers  (2026-07-15T05:12:48Z)
• IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation [78.00035681410348]
  IGL-Nav is an Incremental 3D Gaussian framework for efficient and 3D-aware image-goal navigation.<n>It can handle the more challenging free-view image-goal setting and be deployed on real-world robotic platform.
  arXiv  Detail & Related papers  (2025-08-01T17:59:56Z)
• Zero-shot Inexact CAD Model Alignment from a Single Image [53.37898107159792]
  A practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image.<n>Existing methods rely on supervised training with images and pose annotations, which limits them to a narrow set of object categories.<n>We propose a weakly supervised 9-DoF alignment method for inexact 3D models that requires no pose annotations and generalizes to unseen categories.
  arXiv  Detail & Related papers  (2025-07-04T04:46:59Z)
• ZeroGS: Training 3D Gaussian Splatting from Unposed Images [62.34149221132978]
  We propose ZeroGS to train 3DGS from hundreds of unposed and unordered images. Our method leverages a pretrained foundation model as the neural scene representation. Our method recovers more accurate camera poses than state-of-the-art pose-free NeRF/3DGS methods.
  arXiv  Detail & Related papers  (2024-11-24T11:20:48Z)
• Camera-Pose Robust Crater Detection from Chang'e 5 [18.986915927640396]
  We evaluate the performance of Mask R-CNN for crater detection, comparing models pretrained on simulated data containing off-nadir view angles and to pretraining on real-lunar images. We demonstrate pretraining on real-lunar images is superior despite the lack of images containing off-nadir view angles, achieving detection performance of 63.1 F1-score and ellipse-regression performance of 0.701 intersection over union.
  arXiv  Detail & Related papers  (2024-06-07T01:11:31Z)
• FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models [5.754251195342313]
  We show how to tackle the same task but without training on specific data.<n>We propose FreeZe, a novel solution that harnesses the capabilities of pre-trained geometric and vision foundation models.<n>FreeZe consistently outperforms all state-of-the-art approaches, including competitors extensively trained on synthetic 6D pose estimation data.
  arXiv  Detail & Related papers  (2023-12-01T22:00:14Z)
• FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation [54.25416624924669]
  We propose a Fine-grained Goal Prompting (FGPrompt) method for image-goal navigation. FGPrompt preserves detailed information in the goal image and guides the observation encoder to pay attention to goal-relevant regions. Our method brings significant performance improvement on 3 benchmark datasets.
  arXiv  Detail & Related papers  (2023-10-11T13:19:29Z)
• Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image [85.91935485902708]
  We show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images.
  arXiv  Detail & Related papers  (2023-07-20T16:14:23Z)
• Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images [60.0898989456276]
  We present a new framework named Cas6D for few-shot 6DoF pose estimation that is generalizable and uses only RGB images. To address the false positives of target object detection in the extreme few-shot setting, our framework utilizes a self-supervised pre-trained ViT to learn robust feature representations. Experimental results on the LINEMOD and GenMOP datasets demonstrate that Cas6D outperforms state-of-the-art methods by 9.2% and 3.8% accuracy (Proj-5) under the 32-shot setting.
  arXiv  Detail & Related papers  (2023-06-13T07:45:42Z)
• OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models [51.68715543630427]
  OnePose relies on detecting repeatable image keypoints and is thus prone to failure on low-textured objects. We propose a keypoint-free pose estimation pipeline to remove the need for repeatable keypoint detection. A 2D-3D matching network directly establishes 2D-3D correspondences between the query image and the reconstructed point-cloud model.
  arXiv  Detail & Related papers  (2023-01-18T17:47:13Z)
• Coupled Iterative Refinement for 6D Multi-Object Pose Estimation [64.7198752089041]
  Given a set of known 3D objects and an RGB or RGB-D input image, we detect and estimate the 6D pose of each object. Our approach iteratively refines both pose and correspondence in a tightly coupled manner, allowing us to dynamically remove outliers to improve accuracy.
  arXiv  Detail & Related papers  (2022-04-26T18:00:08Z)
• Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction [2.016317500787292]
  We propose a method for initial camera pose estimation from just a single image. It exploits the ability of deep learning techniques to reliably detect objects regardless of viewing conditions. Experiments prove that the accuracy of the computed pose significantly increases thanks to our method.
  arXiv  Detail & Related papers  (2022-03-09T10:00:52Z)
• Memory-Augmented Reinforcement Learning for Image-Goal Navigation [67.3963444878746]
  We present a novel method that leverages a cross-episode memory to learn to navigate. In order to avoid overfitting, we propose to use data augmentation on the RGB input during training. We obtain this competitive performance from RGB input only, without access to additional sensors such as position or depth.
  arXiv  Detail & Related papers  (2021-01-13T16:30:20Z)
• L6DNet: Light 6 DoF Network for Robust and Precise Object Pose Estimation with Small Datasets [0.0]
  We propose a novel approach to perform 6 DoF object pose estimation from a single RGB-D image. We adopt a hybrid pipeline in two stages: data-driven and geometric. Our approach is more robust and accurate than state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-02-03T17:41:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.