SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.14837 · CVPR · 2023

IMP: Iterative Matching and Pose Estimation with Adaptive Pooling

Roberto Cipolla, Ignas Budvytis, Fei Xue

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 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; 6 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2304.14837.json · badge: /api/ran/2304.14837.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
feixue94/imp-release community
Papers with Code archive
11 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
AttentionalGNN Ran
ran on a synthesized input · constructed an object; no result was computed
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("8c20f7da927c6d44")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

AttentionalPropagation Ran
ran on a synthesized input · constructed an object; no result was computed
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("02facb3753d9d813")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

GraphLoss Ran
ran on a synthesized input · constructed an object; no result was computed
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("5bb60a2bc56f82e0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

KeypointEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("3ef4a124ba7a0333")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

MLP Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("c8e37a8aa3051edc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

MultiHeadedAttention Ran
ran on a synthesized input
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("d174e0da00210ed5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

SharedAttentionalPropagation Ran
ran on a synthesized input
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("3f38d68d9fd0d31b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

arange_like Ran
ran; our contract draft was wrong, not the code
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("4673f355214f8423")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

dual_softmax Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("ddc2bd4ba32ce477")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

normalize_keypoints Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from tzvikif/SuperGlue
pointer only; the stored copy get_code serves, from tzvikif/SuperGlue, is pointer only (licence: NOASSERTION) · get_code("46818e125ab57432")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

sink_algorithm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("f9f5afc23da17c34")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

sinkhorn Ran
ran; our contract draft was wrong, not the code
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("630be194366638dc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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.

AdaGMN Not yet run
unverified (harvested, no recorded run)
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("815c90d5fc5347af")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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. No invocation recorded.

GM Not yet run
unverified (harvested, no recorded run)
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("941f927d44aece73")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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. No invocation recorded.

SAGNN Not yet run
unverified (harvested, no recorded run)
feixue94/imp-release/nets/adgm.py
pointer only (licence: NOASSERTION) · get_code("dd5562511e5279c2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, feixue94/imp-release (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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 13 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
normalize_keypoints
brick of this paper's assembly: helper
4 other papers
2 dated earlier, 2 later
1712.07629 (2017-12)
SuperPoint: Self-Supervised Interest Point Detection and Description
2310.01680 (2023-10)
Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation
and 1 more not named here
arange_like
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2203.12335 (2022-03)
DR.VIC: Decomposition and Reasoning for Video Individual Counting

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

Previous methods solve feature matching and pose estimation using a two-stage process by first finding matches and then estimating the pose. As they ignore the geometric relationships between the two tasks, they focus on either improving the quality of matches or filtering potential outliers, leading to limited efficiency or accuracy. In contrast, we propose an iterative matching and pose estimation framework (IMP) leveraging the geometric connections between the two tasks: a few good matches are enough for a roughly accurate pose estimation; a roughly accurate pose can be used to guide the matching by providing geometric constraints. To this end, we implement a geometry-aware recurrent attention-based module which jointly outputs sparse matches and camera poses. Specifically, for each iteration, we first implicitly embed geometric information into the module via a pose-consistency loss, allowing it to predict geometry-aware matches progressively. Second, we introduce an efficient IMP, called EIMP, to dynamically discard keypoints without potential matches, avoiding redundant updating and significantly reducing the quadratic time complexity of attention computation in transformers. Experiments on YFCC100m, Scannet, and Aachen Day-Night datasets demonstrate that the proposed method outperforms previous approaches in terms of accuracy and efficiency. Code is available at https: //github.com/feixue94/imp-release

For agents

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

get_harvested_code_for_paper("2304.14837")
get_code_for_paper("2304.14837")
have("2304.14837")

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

curl https://syntology.ai/api/ran/2304.14837.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.14837.svg)](https://syntology.ai/paper/2304.14837)

Connect an agent — have() is free.