SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.09213 · CVPR · 2021

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

Marc Pollefeys, Vincent Lepetit, Fredrik Kahl, Paul-Edouard Sarlin, Torsten Sattler, Hugo Germain, Viktor Larsson, Carl Toft, Lars Hammarstrand, Ajaykumar Unagar, Måns Larsson, Ecole Des Ponts

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 1 failure of our instrument; 3 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/2103.09213.json · badge: /api/ran/2103.09213.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
jmorlana/dran community
Papers with Code archive
7 ran · 3 no recorded run
FunctionStatusWhere it lives
AdaptationBlock Ran
ran on a synthesized input · constructed an object; no result was computed
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("dcbcf6c7c35dcc21")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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.

DecoderBlock Ran
ran on a synthesized input · constructed an object; no result was computed
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("73ff98fe01a66ef6")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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.

GeM Ran
ran on a synthesized input · constructed an object; no result was computed
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("79107b69f7e4f56c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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.

L2N Ran
ran on a synthesized input · constructed an object; no result was computed
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("961971793d9e5753")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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.

LocalizationHeadBlock Ran
ran on a synthesized input · constructed an object; no result was computed
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("f753ef150fba5f85")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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.

RetrievalBlock Ran
ran on a synthesized input · constructed an object; no result was computed
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("8f7f65670a0a34dd")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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.

checkpointed Ran
ran; our contract draft was wrong, not the code
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("a75983e92b154d01")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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.

BaseModel Not yet run
unverified (harvested, no recorded run)
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("6428fa4387ff5c9d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

MetaModel Not yet run
unverified (harvested, no recorded run)
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("1d1ea14640fc616e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

UNet Not yet run
unverified (harvested, no recorded run)
jmorlana/dran/dran/lib/models/two_unet_gem.py
pointer only (licence: GPL-3.0) · get_code("484365362394040e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, jmorlana/dran, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 8 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
BaseModel
brick of this paper's assembly: helper
1 other paper
1 later
2304.02008 (2023-04)
GlueStick: Robust Image Matching by Sticking Points and Lines Together
MetaModel
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2304.02008 (2023-04)
GlueStick: Robust Image Matching by Sticking Points and Lines Together

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

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints or ties the model parameters to a specific scene. In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms. We introduce PixLoc, a sceneagnostic neural network that estimates an accurate 6-DoF pose from an image and a 3D model. Our approach is based on the direct alignment of multiscale deep features, casting camera localization as metric learning. PixLoc learns strong data priors by end-to-end training from pixels to pose and exhibits exceptional generalization to new scenes by separating model parameters and scene geometry. The system can localize in large environments given coarse pose priors but also improve the accuracy of sparse feature matching by jointly refining keypoints and poses with little overhead. The code will be publicly available at github.com/cvg/pixloc.

For agents

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

get_harvested_code_for_paper("2103.09213")
get_code_for_paper("2103.09213")
have("2103.09213")

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

curl https://syntology.ai/api/ran/2103.09213.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.09213.svg)](https://syntology.ai/paper/2103.09213)

Connect an agent — have() is free.