SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.12555 · 2022

6D Rotation Representation For Unconstrained Head Pose Estimation

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 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/2202.12555.json · badge: /api/ran/2202.12555.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
thohemp/6drepnet canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from yakhyo/head-pose-estimation
pointer only · get_code("d97ed054442099c9")
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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from yakhyo/head-pose-estimation
pointer only · get_code("7f22d053fb2c79d3")
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.

conv_bn Ran
ran; our contract draft was wrong, not the code
thohemp/6drepnet/sixdrepnet/backbone/repvgg.py
code served (permissive licence) · get_code("7186655759897af6")
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 Sequential. The image it ran in was not recorded. If your copy returns the same type 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 64,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'groups': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
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
draw_axis Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thohemp/6drepnet/sixdrepnet/utils.py
code served (permissive licence) · get_code("9e05b6376777dfab")
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, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (480, 640, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np
import cv2

# Create a small test image (BGR format, as cv2 expects)
img = np.zeros((480, 640, 3), dtype=np.uint8)

# Define angles in degrees
yaw = 30.0
pitch = 20.0
roll = 15.0

# Optional center coordinates (if not provided, function uses image center)
tdx = 320.0
tdy = 240.0

# Size of the axis lines
size = 100

ARGS = {
    "img": img,
    "yaw": yaw,
    "pitch": pitch,
    "roll": roll,
    "tdx": tdx,
    "tdy": tdy,
    "size": size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (480, 640, 3) — shape (480, 640, 3) as a later run recorded it
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
expand_bbox Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from yakhyo/head-pose-estimation
pointer only · get_code("0e7a40594b66badc")
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.

get_list_from_filenames Ran
ran on a synthesized input
thohemp/6drepnet/sixdrepnet/datasets.py
code served (permissive licence) · get_code("5506a49b4dec7c1a")
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, through the batch API) and returned list, 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 tempfile
import os

# Create a temporary file with some test content
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("line1\n")
temp_file.write("line2\n")
temp_file.write("line3\n")
temp_file.close()

ARGS = {
    'file_path': temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 list, ndim 1, dtype family float — a list 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
get_pose_params_from_mat Ran
ran, honoured the contract we drafted
thohemp/6drepnet/sixdrepnet/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from vladhondru25/DF-MoE, is pointer only (licence: NOASSERTION) · get_code("3439d44222ccdc72")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from vladhondru25/DF-MoE, 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.

plot_pose_cube Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thohemp/6drepnet/sixdrepnet/utils.py
code served (permissive licence) · get_code("c9c193a924512abf")
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, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (480, 640, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np
import cv2

# Create a sample image (BGR format for OpenCV)
img = np.ones((480, 640, 3), dtype=np.uint8) * 255

# Define pose angles in degrees
yaw = 15.0
pitch = 10.0
roll = 5.0

# Define face center coordinates
tdx = 320.0
tdy = 240.0

# Define cube size
size = 150.0

ARGS = {
    'img': img,
    'yaw': yaw,
    'pitch': pitch,
    'roll': roll,
    'tdx': tdx,
    'tdy': tdy,
    'size': size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (480, 640, 3) — shape (480, 640, 3) as a later run recorded it
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 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, 7 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 6 later) and 1 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
conv_bn 10 other papers
4 dated earlier, 6 later
2003.13678 (2020-03)
Designing Network Design Spaces
2101.03697 (2021-01)
RepVGG: Making VGG-style ConvNets Great Again
2105.01883 (2021-05)
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
and 7 more not named here
conv1x1 4 other papers
3 dated earlier, 1 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1710.00925 (2017-10)
Fine-Grained Head Pose Estimation Without Keypoints
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
and 1 more not named here
conv3x3 4 other papers
3 dated earlier, 1 later
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1710.00925 (2017-10)
Fine-Grained Head Pose Estimation Without Keypoints
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
and 1 more not named here
get_pose_params_from_mat 2 other papers
2 later
Zhang_TokenHPE_Learning_Orientation_Tokens_for_Efficient_Head_Pose_Estimation_via_CVPR_2023_paper (2023 (year only))
TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers
2608.23363 (2026-08)
DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts
draw_axis 1 other paper
1 later
Zhang_TokenHPE_Learning_Orientation_Tokens_for_Efficient_Head_Pose_Estimation_via_CVPR_2023_paper (2023 (year only))
TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers
expand_bbox 1 other paper
1 dated earlier
1710.00925 (2017-10)
Fine-Grained Head Pose Estimation Without Keypoints
plot_pose_cube 1 other paper
1 later
Zhang_TokenHPE_Learning_Orientation_Tokens_for_Efficient_Head_Pose_Estimation_via_CVPR_2023_paper (2023 (year only))
TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers

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

In this paper, we present a method for unconstrained end-to-end head pose estimation. We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This way, our method can learn the full rotation appearance which is contrary to previous approaches that restrict the pose prediction to a narrow-angle for satisfactory results. In addition, we propose a geodesic distance-based loss to penalize our network with respect to the SO(3) manifold geometry. Experiments on the public AFLW2000 and BIWI datasets demonstrate that our proposed method significantly outperforms other state-of-the-art methods by up to 20\%. We open-source our training and testing code along with our pre-trained models: https://github.com/thohemp/6DRepNet.

For agents

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

get_harvested_code_for_paper("2202.12555")
get_code_for_paper("2202.12555")
have("2202.12555")

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

curl https://syntology.ai/api/ran/2202.12555.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.12555.svg)](https://syntology.ai/paper/2202.12555)

Connect an agent — have() is free.