SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.12787 · 2023

EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 0 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 3 failures of our instrument; 2 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/2303.12787.json · badge: /api/ran/2303.12787.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
tjiiv-cprg/epro-pnp-v2 canonical (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
tjiiv-cprg/epro-pnp community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
draw_orient_density Ran
ran on a synthesized input
tjiiv-cprg/epro-pnp/EPro-PnP-6DoF/lib/utils/draw_orient_density.py
pointer only (licence: Apache-2.0) · get_code("5a8477f0b7df5a2a")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, tjiiv-cprg/epro-pnp, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

euler_angles_to_matrix Ran
ran; our contract draft was wrong, not the code
tjiiv-cprg/epro-pnp/EPro-PnP-6DoF/lib/ops/rotation_conversions.py
pointer only (licence: Apache-2.0) · get_code("97dae9745013aa60")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, tjiiv-cprg/epro-pnp, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

matrix_to_quaternion Ran
ran; our contract draft was wrong, not the code
tjiiv-cprg/epro-pnp/EPro-PnP-6DoF/lib/ops/rotation_conversions.py
pointer only (licence: Apache-2.0) · get_code("e59f47c519114fa0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, tjiiv-cprg/epro-pnp, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

obj2idx Ran
ran on a synthesized input
tjiiv-cprg/epro-pnp/EPro-PnP-6DoF/lib/ref.py
pointer only (licence: Apache-2.0) · get_code("5253f1ce3347b571")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, tjiiv-cprg/epro-pnp, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

quaternion_to_matrix Ran
ran; our contract draft was wrong, not the code
tjiiv-cprg/epro-pnp/EPro-PnP-6DoF/lib/ops/rotation_conversions.py
pointer only (licence: Apache-2.0) · get_code("e0238352153c0549")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, tjiiv-cprg/epro-pnp, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

str2bool Ran
ran, violated the contract we drafted
tjiiv-cprg/epro-pnp/EPro-PnP-6DoF/lib/config.py
pointer only (licence: Apache-2.0) · get_code("f017532fc389cbfe")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, tjiiv-cprg/epro-pnp, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

download Not yet run
unverified (harvested, no recorded run)
tjiiv-cprg/epro-pnp-v2/EPro-PnP-6DoF_v2/lib/utils/fs.py
code served (permissive licence) · get_code("78300875c6a51f76")
How it ran

no invocation recorded.

set_logger_dir Not yet run
unverified (harvested, no recorded run)
tjiiv-cprg/epro-pnp/EPro-PnP-6DoF/lib/utils/fancy_logger.py
pointer only (licence: Apache-2.0) · get_code("c4444b8ff1266dfa")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, tjiiv-cprg/epro-pnp, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 4 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
str2bool 82 other papers
59 dated earlier, 20 later, 3 same year, order not determinable
1510.03055 (2015-10)
A Diversity-Promoting Objective Function for Neural Conversation Models
1703.06490 (2017-03)
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
1710.10467 (2017-10)
Generalized End-to-End Loss for Speaker Verification
and 79 more not named here
matrix_to_quaternion 4 other papers
4 later
2306.03117 (2023-06)
Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
2403.07494 (2024-03)
SemGauss-SLAM: Dense Semantic Gaussian Splatting SLAM
and 1 more not named here
euler_angles_to_matrix 3 other papers
3 later
2306.03117 (2023-06)
Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
2404.11735 (2024-04)
Learning with 3D rotations, a hitchhiker's guide to SO(3)
quaternion_to_matrix 3 other papers
3 later
2306.03117 (2023-06)
Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
2404.03736 (2024-04)
SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer

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

Locating 3D objects from a single RGB image via Perspective-n-Point (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, allowing for partial learning of 2D-3D point correspondences by backpropagating the gradients of pose loss. Yet, learning the entire correspondences from scratch is highly challenging, particularly for ambiguous pose solutions, where the globally optimal pose is theoretically non-differentiable w.r.t. the points. In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose with differentiable probability density on the SE(3) manifold. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle generalizes previous approaches, and resembles the attention mechanism. EPro-PnP can enhance existing correspondence networks, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation benchmark. Furthermore, EPro-PnP helps to explore new possibilities of network design, as we demonstrate a novel deformable correspondence network with the state-of-the-art pose accuracy on the nuScenes 3D object detection benchmark. Our code is available at https://github.com/tjiiv-cprg/EPro-PnP-v2.

For agents

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

get_harvested_code_for_paper("2303.12787")
get_code_for_paper("2303.12787")
have("2303.12787")

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

curl https://syntology.ai/api/ran/2303.12787.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.12787.svg)](https://syntology.ai/paper/2303.12787)

Connect an agent — have() is free.