SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.02541 · 2018

Segmentation-driven 6D Object Pose Estimation

arXiv · PDF · Open in the Atlas

Code that ran

7 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, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 1 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/1812.02541.json · badge: /api/ran/1812.02541.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
AP-EPFL/DA-segmentation-driven-pose community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
add_err Ran
ran on a synthesized input
AP-EPFL/DA-segmentation-driven-pose/metric.py
code served (permissive licence) · get_code("a8996657dfd0bebd")
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 float64, ndim 0, 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 numpy as np

# gt_pose: a 4x4 transformation matrix (homogeneous coordinates)
gt_pose = np.array([
    [1.0, 0.0, 0.0, 0.1],
    [0.0, 1.0, 0.0, 0.2],
    [0.0, 0.0, 1.0, 0.3],
    [0.0, 0.0, 0.0, 1.0]
])

# est_pose: a 4x4 transformation matrix (slightly different from gt_pose)
est_pose = np.array([
    [1.0, 0.0, 0.0, 0.15],
    [0.0, 1.0, 0.0, 0.25],
    [0.0, 0.0, 1.0, 0.35],
    [0.0, 0.0, 0.0, 1.0]
])

# model: a set of 3D points (Nx3 array)
# Using 2 points with 3 coordinates each
model = np.array([
    [0.0, 0.0, 0.0],
    [1.0, 1.0, 1.0]
])

ARGS = {
    "gt_pose": gt_pose,
    "est_pose": est_pose,
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
adds_err Ran
ran on a synthesized input
AP-EPFL/DA-segmentation-driven-pose/metric.py
code served (permissive licence) · get_code("89e617351e50af88")
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 float32, ndim 0, dtype family float, shape () 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

# Set random seed for reproducibility
np.random.seed(0)

# Create a small 3D model (points)
# The function expects a 2D array of 3D points that will be transformed
model = np.random.randn(10, 3).astype(np.float32)

# Create ground truth pose (4x4 transformation matrix)
gt_pose = np.eye(4, dtype=np.float32)
gt_pose[:3, :3] = np.array([
    [0.9, -0.1, 0.0],
    [0.1, 0.9, 0.0],
    [0.0, 0.0, 1.0]
], dtype=np.float32)
gt_pose[:3, 3] = np.array([0.5, 0.5, 0.5], dtype=np.float32)

# Create estimated pose (4x4 transformation matrix) - slightly different from gt_pose
est_pose = np.eye(4, dtype=np.float32)
est_pose[:3, :3] = np.array([
    [0.85, -0.15, 0.05],
    [0.15, 0.88, -0.05],
    [-0.05, 0.05, 0.99]
], dtype=np.float32)
est_pose[:3, 3] = np.array([0.6, 0.55, 0.48], dtype=np.float32)

ARGS = {
    "gt_pose": gt_pose,
    "est_pose": est_pose,
    "model": model,
    "sample_num": 100
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float32, ndim 0, dtype family float, shape () — shape () 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
convert2cpu Ran
ran on a synthesized input
AP-EPFL/DA-segmentation-driven-pose/utils.py
code served (permissive licence) · get_code("1f78cee6c9c61b60")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# The function convert2cpu takes a gpu_matrix and converts it to a CPU FloatTensor
# It calls .shape on the input and .copy_() on a new tensor
# So gpu_matrix needs to be a tensor with a shape attribute

gpu_matrix = torch.randn(2, 4)

ARGS = {
    "gpu_matrix": gpu_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
copy_model Ran
ran on a synthesized input
AP-EPFL/DA-segmentation-driven-pose/multiflow.py
code served (permissive licence) · get_code("668acc86a68b9fc2")
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 SimpleModel. 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
import copy

torch.manual_seed(0)

# Define a simple model for testing
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Create a model instance
model = SimpleModel()

# Initialize parameters with some values
for param in model.parameters():
    param.data.fill_(1.0)

ARGS = {
    "model": model,
    "share_params": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel output the recorded ndim 0 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
get_class_colors Ran
ran on a synthesized input
AP-EPFL/DA-segmentation-driven-pose/utils.py
code served (permissive licence) · get_code("fa69fbf311f83d41")
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 tuple, ndim 1, dtype family int; 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 torch
import numpy as np

# The function get_class_colors takes a class_id integer parameter
# It uses class_id to index into a list of color names
# The valid range is 0 to len(colornames)-1 where colornames has 147 colors

ARGS = {
    'class_id': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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 int — 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
parse_cfg Ran
ran on a synthesized input
AP-EPFL/DA-segmentation-driven-pose/cfg.py
code served (permissive licence) · get_code("b5bfd6725600f300")
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 config file for testing
temp_fd, temp_path = tempfile.mkstemp(suffix='.cfg', text=True)
os.close(temp_fd)

# Write a sample config file content
config_content = """# This is a comment
[convolutional]
filters=32
kernel_size=3
stride=1
pad=1
activation=relu

[pooling]
type=max
kernel_size=2
stride=2

# Another comment
[connected]
output=10
activation=softmax
"""

with open(temp_path, 'w') as f:
    f.write(config_content)

ARGS = {
    'cfgfile': temp_path
}
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
vertices_reprojection Ran
ran on a synthesized input
AP-EPFL/DA-segmentation-driven-pose/utils.py
code served (permissive licence) · get_code("1273cfd50cab332d")
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 2, dtype family float, shape (2, 2) 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

# Set random seed for reproducibility
np.random.seed(0)

# Create small test data
# vertices: shape (N, 3) - 3D points
vertices = np.array([
    [0.1, 0.2, 1.0],
    [0.3, 0.4, 2.0],
], dtype=np.float32)

# rt: shape (4, 4) - rotation and translation matrix (4x4 homogeneous)
# rt[:3, :3] is rotation (3x3), rt[:3, 3] is translation (3,)
rt = np.array([
    [1.0, 0.0, 0.0, 0.1],
    [0.0, 1.0, 0.0, 0.2],
    [0.0, 0.0, 1.0, 0.3],
    [0.0, 0.0, 0.0, 1.0],
], dtype=np.float32)

# k: shape (3, 3) - camera intrinsic matrix
k = np.array([
    [500.0, 0.0, 320.0],
    [0.0, 500.0, 240.0],
    [0.0, 0.0, 1.0],
], dtype=np.float32)

ARGS = {
    "vertices": vertices,
    "rt": rt,
    "k": k,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) 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
rot_error Not yet run
unverified (harvested, no recorded run)
AP-EPFL/DA-segmentation-driven-pose/metric.py
code served (permissive licence) · get_code("8ab2b01c7f866f10")
How it ran

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm. In both cases, the object is treated as a global entity, and a single pose estimate is computed. As a consequence, the resulting techniques can be vulnerable to large occlusions. In this paper, we introduce a segmentation-driven 6D pose estimation framework where each visible part of the objects contributes a local pose prediction in the form of 2D keypoint locations. We then use a predicted measure of confidence to combine these pose candidates into a robust set of 3D-to-2D correspondences, from which a reliable pose estimate can be obtained. We outperform the state-of-the-art on the challenging Occluded-LINEMOD and YCB-Video datasets, which is evidence that our approach deals well with multiple poorly-textured objects occluding each other. Furthermore, it relies on a simple enough architecture to achieve real-time performance.

For agents

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

get_harvested_code_for_paper("1812.02541")
get_code_for_paper("1812.02541")
have("1812.02541")

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

curl https://syntology.ai/api/ran/1812.02541.json

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

[![Syntology run record](https://syntology.ai/api/ran/1812.02541.svg)](https://syntology.ai/paper/1812.02541)

Connect an agent — have() is free.