SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1810.03065 · 2018

Deep Model-Based 6D Pose Refinement in RGB

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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; 4 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/1810.03065.json · badge: /api/ran/1810.03065.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
fabi92/eccv18-rgb_pose_refinement canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
FunctionStatusWhere it lives
backproject Ran
ran on a synthesized input
fabi92/eccv18-rgb_pose_refinement/rendering/utils.py
code served (permissive licence) · get_code("08bec8ecb354a58b")
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 float, shape (4, 3, 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

# Construct a small depth map (height=4, width=3)
depth = np.random.rand(4, 3) * 5.0  # depth values between 0-5

# Construct camera intrinsics matrix (3x3)
# Standard form: [[fx, 0, cx], [0, fy, cy], [0, 0, 1]]
cam = np.array([
    [500.0, 0.0, 1.5],      # fx, 0, cx
    [0.0, 500.0, 2.0],      # 0, fy, cy
    [0.0, 0.0, 1.0]         # 0, 0, 1
], dtype=np.float64)

ARGS = {
    "depth": depth,
    "cam": cam
}
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 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 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
depthTo3D Ran
ran on a synthesized input
fabi92/eccv18-rgb_pose_refinement/rendering/utils.py
code served (permissive licence) · get_code("876f74263b3b9625")
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 1, dtype family float, shape (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

# Create a 2D point (image coordinates)
pt = np.array([320.5, 240.3])

# Create a depth value
z = 2.5

# Create a camera intrinsics matrix (3x3)
# Typical format: [[fx, 0, ox], [0, fy, oy], [0, 0, 1]]
cam = np.array([
    [500.0, 0.0, 320.0],
    [0.0, 500.0, 240.0],
    [0.0, 0.0, 1.0]
])

ARGS = {
    "pt": pt,
    "z": z,
    "cam": cam
}
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 1, dtype family float, shape (3,) — shape (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
find_symmetry_quaternions Ran
ran on a synthesized input
fabi92/eccv18-rgb_pose_refinement/utils/quaternion.py
code served (permissive licence) · get_code("fd09c610a2bab0f7")
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 2, 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
from functools import partial
from scipy.optimize import minimize

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

# Create sample data
# The function expects data with shape (n_samples, 4) where:
# - Column 0: some identifier or value (not used in function)
# - Columns 1-3: xyz coordinates
data = np.random.randn(2, 4).astype(np.float64)

# Ensure the xyz part (columns 1-3) has reasonable values
data[:, 1:4] = np.random.randn(2, 3) * 10

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — 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
matrix2quaternion Ran
ran on a synthesized input
fabi92/eccv18-rgb_pose_refinement/utils/quaternion.py
code served (permissive licence) · get_code("f119edd0d30079e5")
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 1, dtype family float, shape (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 numpy as np

# Create a valid 3x3 rotation matrix
# Using a simple rotation matrix (90 degrees around z-axis)
m = np.array([
    [0.0, -1.0, 0.0],
    [1.0, 0.0, 0.0],
    [0.0, 0.0, 1.0]
], dtype=np.float64)

ARGS = {
    "m": m
}
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 1, dtype family float, shape (4,) — shape (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
project Ran
ran on a synthesized input
fabi92/eccv18-rgb_pose_refinement/rendering/utils.py
code served (permissive licence) · get_code("49c77802b67edcf2")
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 int, 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

# Create sample 3D points (N, 3)
# Using N=2 points, each with x, y, z coordinates
points_3d = np.array([
    [1.0, 2.0, 5.0],
    [0.5, 1.5, 4.0]
], dtype=np.float32)

# Create camera intrinsics matrix (3, 3)
# Typical format: [[fx, 0, cx], [0, fy, cy], [0, 0, 1]]
# Using distinct dimensions: 4x3 to avoid ambiguity
cam = np.array([
    [500.0, 0.0, 320.0],
    [0.0, 500.0, 240.0],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

ARGS = {
    "points_3d": points_3d,
    "cam": cam
}
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 int, 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
quaternion_to_euler Ran
ran on a synthesized input
fabi92/eccv18-rgb_pose_refinement/utils/quaternion.py
code served (permissive licence) · get_code("e875ab48d8844c1a")
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 numpy as np
import torch

# Create a valid quaternion (normalized)
# A quaternion is represented as [w, x, y, z]
# For a valid rotation quaternion, w^2 + x^2 + y^2 + z^2 = 1
q = np.array([0.7071068, 0.7071068, 0.0, 0.0], dtype=np.float32)

ARGS = {
    "q": q
}
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 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
singleton Ran
ran on a synthesized input
fabi92/eccv18-rgb_pose_refinement/rendering/renderer.py
code served (permissive licence) · get_code("7688c81b21c2784f")
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 function. 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)

# The singleton decorator takes a class `cls` as parameter
# It returns a get_instance function that takes `size` and `cam` arguments
# The decorator expects cls to be callable with (size, cam) arguments

class DummyClass:
    """A simple class that accepts size and cam parameters"""
    def __init__(self, size, cam):
        self.size = size
        self.cam = cam

ARGS = {
    "cls": DummyClass
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
loadSIXDBench Not yet run
unverified (harvested, no recorded run)
fabi92/eccv18-rgb_pose_refinement/utils/utils.py
code served (permissive licence) · get_code("3707ab6518aed51e")
How it ran

no invocation recorded.

load_gt Not yet run
unverified (harvested, no recorded run)
fabi92/eccv18-rgb_pose_refinement/utils/sixd.py
code served (permissive licence) · get_code("02e3d7af9e8b3225")
How it ran

no invocation recorded.

load_info Not yet run
unverified (harvested, no recorded run)
fabi92/eccv18-rgb_pose_refinement/utils/sixd.py
code served (permissive licence) · get_code("ad670f8eff1c8d2d")
How it ran

no invocation recorded.

load_yaml Not yet run
unverified (harvested, no recorded run)
fabi92/eccv18-rgb_pose_refinement/utils/sixd.py
code served (permissive licence) · get_code("42001485c89d0e7f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 9 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
load_yaml 1 other paper
1 later
1812.01387 (2018-12)
Estimating 6D Pose From Localizing Designated Surface Keypoints
singleton 1 other paper
1 later
1908.07433 (2019-08)
Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation

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

We present a novel approach for model-based 6D pose refinement in color data. Building on the established idea of contour-based pose tracking, we teach a deep neural network to predict a translational and rotational update. At the core, we propose a new visual loss that drives the pose update by aligning object contours, thus avoiding the definition of any explicit appearance model. In contrast to previous work our method is correspondence-free, segmentation-free, can handle occlusion and is agnostic to geometrical symmetry as well as visual ambiguities. Additionally, we observe a strong robustness towards rough initialization. The approach can run in real-time and produces pose accuracies that come close to 3D ICP without the need for depth data. Furthermore, our networks are trained from purely synthetic data and will be published together with the refinement code to ensure reproducibility.

For agents

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

get_harvested_code_for_paper("1810.03065")
get_code_for_paper("1810.03065")
have("1810.03065")

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

curl https://syntology.ai/api/ran/1810.03065.json

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

[![Syntology run record](https://syntology.ai/api/ran/1810.03065.svg)](https://syntology.ai/paper/1810.03065)

Connect an agent — have() is free.