CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation

Hugging Face Daily Papers Papers
cross-view geo-localization pose-estimation transformer image-retrieval unified-framework

Summary

CIPER is a unified transformer framework that jointly performs city-scale retrieval and precise 3-DoF pose estimation from cross-view images, overcoming limitations of cascade pipelines.

Cross-view geo-localization estimates the geographic location of a ground image by matching it against an aerial image database. Existing methods tackle this through either large-scale retrieval or precise pose estimation, but not both: retrieval-based methods enable wide-area search at the cost of localization accuracy, while pose estimation methods achieve high precision within only a narrow search space. Naively cascading these pipelines introduces error propagation and inconsistent feature representations. We formulate cross-view geo-localization as a unified problem requiring simultaneous city-scale retrieval and precise 3-DoF pose estimation. We propose CIPER (Cross-view Image-retrieval and Pose-estimation transformER), a single architecture that jointly performs both tasks through mutually beneficial feature learning. CIPER uses a shared transformer encoder with task-specific tokens to disentangle global retrieval features from spatial localization cues. To bridge the large domain gap between ground and aerial views, we introduce a two-way transformer pose decoder that uses ground features as spatial queries for bidirectional cross-attention. A set prediction strategy further enables stable 3-DoF regression under a unified multi-task objective. Experiments on VIGOR, KITTI, and Ford Multi-AV demonstrate competitive performance, especially under limited field-of-view and arbitrary orientation conditions. Code is available at https://github.com/yurimjeon1892/CIPER.
Original Article
View Cached Full Text

Cached at: 06/09/26, 12:41 PM

Paper page - CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation

Source: https://huggingface.co/papers/2606.05011

Abstract

CIPER is a unified cross-view geo-localization framework that simultaneously performs city-scale retrieval and precise 3-DoF pose estimation using a shared transformer encoder and two-way pose decoder.

Cross-view geo-localizationestimates the geographic location of a ground image by matching it against an aerial image database. Existing methods tackle this through eitherlarge-scale retrievalorprecise pose estimation, but not both: retrieval-based methods enable wide-area search at the cost of localization accuracy, while pose estimation methods achieve high precision within only a narrow search space. Naively cascading these pipelines introduces error propagation and inconsistent feature representations. We formulatecross-view geo-localizationas a unified problem requiring simultaneous city-scale retrieval and precise 3-DoF pose estimation. We propose CIPER (Cross-view Image-retrieval and Pose-estimation transformER), a single architecture that jointly performs both tasks through mutually beneficial feature learning. CIPER uses a sharedtransformer encoderwithtask-specific tokensto disentangle global retrieval features from spatial localization cues. To bridge the large domain gap between ground and aerial views, we introduce atwo-way transformer pose decoderthat uses ground features as spatial queries for bidirectionalcross-attention. Aset prediction strategyfurther enables stable 3-DoF regression under a unifiedmulti-task objective. Experiments on VIGOR, KITTI, and Ford Multi-AV demonstrate competitive performance, especially under limited field-of-view and arbitrary orientation conditions. Code is available at https://github.com/yurimjeon1892/CIPER.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2606\.05011

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.05011 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.05011 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.05011 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Hugging Face Daily Papers

PaGeR adapts the multi-view perspective foundation model Depth Anything 3 to predict scale-invariant and metric depth, surface normals, and sky segmentation from a single equirectangular image, using a fixed cubemap representation that keeps VRAM and runtime constant. The paper also releases the ZüriPano and PanoInfinigen datasets.

CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage

Hugging Face Daily Papers

This paper proposes COVER, a training-free method for converting 3D assets into sparse panoramic RGB-D-pose data with complete scene coverage and low redundancy, and introduces the CM-EVS dataset containing 36,373 curated frames from indoor and outdoor scenes.

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video

Hugging Face Daily Papers

ReViV is a unified framework for holistic egocentric 4D reconstruction that simultaneously reconstructs viewer (body, hand, gaze) and view (depth, camera trajectory) dynamics from a single monocular RGB video using a Masked Generative Egocentric Transformer, achieving state-of-the-art accuracy and efficiency.