SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.04185 · 2026

ImLoc: Revisiting Visual Localization with Image-based Representation

Marc Pollefeys, Fangjinhua Wang, Xudong Jiang, Christoph Vogel, Silvano Galliani

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
cvg/Hierarchical-Localization canonical 1 of 15
FunctionStatusWhere it lives
get_scan_pose Ran cvg/Hierarchical-Localization/hloc/localize_inloc.py
code served (permissive licence) · get_code("dc696698a6226f06")
assign_keypoints Not yet run cvg/Hierarchical-Localization/hloc/match_dense.py
code served (permissive licence) · get_code("22955be0648ea8e7")
camera_center_to_translation Not yet run cvg/Hierarchical-Localization/hloc/colmap_from_nvm.py
code served (permissive licence) · get_code("779d477d79ec6d0d")
find_unique_new_pairs Not yet run cvg/Hierarchical-Localization/hloc/match_features.py
code served (permissive licence) · get_code("edf11e79e54a8ad5")
get_descriptors Not yet run cvg/Hierarchical-Localization/hloc/pairs_from_retrieval.py
code served (permissive licence) · get_code("2a719885fef4ac52")
get_grouped_ids Not yet run cvg/Hierarchical-Localization/hloc/match_dense.py
code served (permissive licence) · get_code("903ef22b452ab670")
get_pairwise_distances Not yet run cvg/Hierarchical-Localization/hloc/pairs_from_poses.py
code served (permissive licence) · get_code("6f19b2c021e984d1")
interpolate_scan Not yet run cvg/Hierarchical-Localization/hloc/localize_inloc.py
code served (permissive licence) · get_code("f5474909d669b0e5")
main Not yet run cvg/Hierarchical-Localization/hloc/extract_features.py
code served (permissive licence) · get_code("18761bb93ffb8441")
pairs_from_score_matrix Not yet run cvg/Hierarchical-Localization/hloc/pairs_from_retrieval.py
code served (permissive licence) · get_code("46a048d57a30cd04")
parse_names Not yet run cvg/Hierarchical-Localization/hloc/pairs_from_retrieval.py
code served (permissive licence) · get_code("8b551ebc7c4ea16a")
quaternion_to_rotation_matrix Not yet run cvg/Hierarchical-Localization/hloc/colmap_from_nvm.py
code served (permissive licence) · get_code("f7dc6973dc8a4981")
recover_database_images_and_ids Not yet run cvg/Hierarchical-Localization/hloc/colmap_from_nvm.py
code served (permissive licence) · get_code("53d3a86babec71bb")
resize_image Not yet run cvg/Hierarchical-Localization/hloc/extract_features.py
code served (permissive licence) · get_code("47ffaeadde70c45c")
to_cpts Not yet run cvg/Hierarchical-Localization/hloc/match_dense.py
code served (permissive licence) · get_code("e54750836225cbe0")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structurebased, which achieve high accuracy but require a centralized reconstruction and are difficult to update. In this work, we revisit visual localization with a 2D image-based representation and propose to augment each image with estimated depth maps to capture the geometric structure. Supported by the effective use of dense matchers, this representation is not only easy to build and maintain, but achieves highest accuracy in challenging conditions. With compact compression and a GPU-accelerated LO-RANSAC implementation, the whole pipeline is efficient in both storage and computation and allows for a flexible trade-off between accuracy and highest memory efficiency. Our method achieves a new state-of-the-art accuracy on various standard benchmarks and outperforms existing memory-efficient methods at comparable map sizes. Code will be available at https://github.com/cvg/Hierarchical-Localization

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.04185")
get_code_for_paper("2601.04185")
have("2601.04185")

Connect an agent — have() is free.