SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.08359 · CVPR · 2024

Learning to Produce Semi-dense Correspondences for Visual Localization

Soohwan Song, Sungho Jo, Khang Truong Giang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.08359.json · badge: /api/ran/2402.08359.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
TruongKhang/DeViLoc canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
read_cameras_binary Ran
ran; our contract draft was wrong, not the code
TruongKhang/DeViLoc/deviloc/utils/read_write_model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from will-zzy/siggraph_asia, is pointer only (licence: NOASSERTION) · get_code("a10bf79d34938dbd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from will-zzy/siggraph_asia, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_cameras_text Ran
ran; our contract draft was wrong, not the code
TruongKhang/DeViLoc/deviloc/utils/read_write_model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from will-zzy/siggraph_asia, is pointer only (licence: NOASSERTION) · get_code("c424ebf4a6c32cbd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from will-zzy/siggraph_asia, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_next_bytes Ran
ran, honoured the contract we drafted
TruongKhang/DeViLoc/deviloc/utils/read_write_model.py
code served (permissive licence) · get_code("56858e04e6fdb2ff")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import struct
import io

# Create a binary file-like object with test data
# We'll pack some values and then read them back
test_data = struct.pack('<hfi', 42, 3.14, 100)
fid = io.BytesIO(test_data)

ARGS = {
    'fid': fid,
    'num_bytes': 10,  # 2 bytes (h) + 4 bytes (f) + 4 bytes (i) = 10 bytes
    'format_char_sequence': 'hfi',
    'endian_character': '<'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 3 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
read_next_bytes 70 other papers
31 dated earlier, 1 the same month, 38 later
1804.00650 (2018-04)
DeepMVS: Learning Multi-view Stereopsis
1902.10556 (2019-02)
Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
and 67 more not named here
read_cameras_text 37 other papers
23 dated earlier, 14 later
1902.10556 (2019-02)
Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
1912.06378 (2019-12)
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
1912.11744 (2019-12)
Planar Prior Assisted PatchMatch Multi-View Stereo
and 34 more not named here
read_cameras_binary 15 other papers
7 dated earlier, 8 later
2207.09137 (2022-07)
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild
2304.09987 (2023-04)
Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra
2305.17398 (2023-05)
NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
and 12 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

This study addresses the challenge of performing visual localization in demanding conditions such as nighttime scenarios, adverse weather, and seasonal changes. While many prior studies have focused on improving image matching performance to facilitate reliable dense keypoint matching between images, existing methods often heavily rely on predefined feature points on a reconstructed 3D model. Consequently, they tend to overlook unobserved keypoints during the matching process. Therefore, dense keypoint matches are not fully exploited, leading to a notable reduction in accuracy, particularly in noisy scenes. To tackle this issue, we propose a novel localization method that extracts reliable semi-dense 2D-3D matching points based on dense keypoint matches. This approach involves regressing semi-dense 2D keypoints into 3D scene coordinates using a point inference network. The network utilizes both geometric and visual cues to effectively infer 3D coordinates for unobserved keypoints from the observed ones. The abundance of matching information significantly enhances the accuracy of camera pose estimation, even in scenarios involving noisy or sparse 3D models. Comprehensive evaluations demonstrate that the proposed method outperforms other methods in challenging scenes and achieves competitive results in large-scale visual localization benchmarks. The code will be available at https://github.com/TruongKhang/DeViLoc.

For agents

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

get_harvested_code_for_paper("2402.08359")
get_code_for_paper("2402.08359")
have("2402.08359")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.08359.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.08359.svg)](https://syntology.ai/paper/2402.08359)

Connect an agent — have() is free.