SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1901.04780 · 2019

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

arXiv · PDF · Open in the Atlas

Code that ran

17 of 19 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 15 have no contract verdict; 2 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/1901.04780.json · badge: /api/ran/1901.04780.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
RiplleYang/DenseFusion community (classifier label)
classifier basis not recorded on the link
10 ran · 1 no recorded run
caoquan95/6D-pose-project community (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
cxt98/Densefusion-transparency reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
RiplleYang/DenseFusion/lib/extractors.py
pointer only (licence: MIT); the stored copy get_code serves, from hkchengrex/Tracking-Anything-with-DEVA, is pointer only (licence: NOASSERTION) · get_code("48f5a5ec1d5dd2ef")
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 hkchengrex/Tracking-Anything-with-DEVA, 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.

depth_to_img Ran
ran on a synthesized input
caoquan95/6D-pose-project/lib/utils.py
code served (permissive licence) · get_code("9ed4d18190c7e529")
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)

# Create a small depth tensor with distinct dimensions
# Shape: (2, 4) - batch of 2, spatial dimension of 4
tensor = torch.rand(2, 4) * 100  # Random values scaled to 0-100 range

ARGS = {
    "tensor": tensor
}
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
get_bbox Ran
ran on a synthesized input
RiplleYang/DenseFusion/datasets/linemod/dataset.py
code served (permissive licence) · get_code("8a2471fdc7dceb0b")
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

torch.manual_seed(0)

# The function get_bbox takes a single parameter: bbox
# Looking at the function body, bbox is indexed as:
# bbox[0], bbox[1], bbox[2], bbox[3]
# So it needs to be a sequence with at least 4 elements

# bbox appears to be in format [x, y, width, height] based on the logic:
# bbx = [bbox[1], bbox[1] + bbox[3], bbox[0], bbox[0] + bbox[2]]
# This creates [y, y+height, x, x+width]

# Create a simple bbox: [x, y, width, height]
bbox = [100, 150, 80, 120]

ARGS = {
    "bbox": bbox
}
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
im_convert Ran
ran on a synthesized input
caoquan95/6D-pose-project/lib/utils.py
code served (permissive licence) · get_code("0b035b9e712d31ef")
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, 5, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a tensor that matches what im_convert expects:
# - Should be on CPU or a device
# - Has shape (batch, channels, height, width) based on transpose(1, 2, 0)
# - After squeeze and transpose, becomes (height, width, channels)
# The function expects 3 channels (RGB) based on the normalization arrays

tensor = torch.randn(1, 3, 4, 5)

ARGS = {
    'tensor': tensor
}
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 ndarray, ndim 3, dtype family float, shape (4, 5, 3) — shape (4, 5, 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
im_grad Ran
ran on a synthesized input
caoquan95/6D-pose-project/lib/loss_depth.py
code served (permissive licence) · get_code("fec9b68daa13babb")
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 5, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn

torch.manual_seed(0)

# The function expects an image tensor
# Looking at the function body:
# - img is passed to torch.mean(img, 1, True) which means it should have shape (batch, channels, height, width)
# - The mean is taken over dimension 1 (channels)
# - The result is passed to Conv2d which expects (batch, 1, height, width)
# So img should be a 4D tensor with shape (batch, channels, height, width)

# Create a small image tensor: batch_size=2, channels=3, height=4, width=5
img = torch.randn(2, 3, 4, 5)

ARGS = {
    "img": img
}
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 tuple, ndim 5, 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
lg10 Ran
ran on a synthesized input
caoquan95/6D-pose-project/lib/evaluate.py
code served (permissive licence) · get_code("d57dd7273b4e8018")
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
import math

torch.manual_seed(0)

# The function lg10(x) takes a single parameter x
# and computes log base 10 of x using torch operations.
# x needs to be a torch tensor with numeric values > 0
# (since we're taking the logarithm)

x = torch.tensor([[1.0, 10.0, 100.0, 1000.0],
                   [0.1, 0.01, 2.5, 7.3]], dtype=torch.float32)

ARGS = {
    "x": x
}
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
loss_calculation Ran
ran on a synthesized input
RiplleYang/DenseFusion/vanilla_segmentation/loss.py
code served (permissive licence) · get_code("18bb339914e06ee3")
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 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function expects:
# - semantic: tensor of shape (bs, 22, 480*640) that gets reshaped to (bs*480*640, 22)
# - target: tensor that gets reshaped to (bs*480*640,) with values in range [0, 21]

bs = 2
pix_num = 480 * 640
num_classes = 22

# semantic: (bs, 22, pix_num) - logits for 22 classes
semantic = torch.randn(bs, num_classes, pix_num)

# target: (bs, pix_num) - class indices in range [0, 21]
target = torch.randint(0, num_classes, (bs, pix_num))

ARGS = {
    "semantic": semantic,
    "target": target,
}
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 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
mask_to_bbox Ran
ran on a synthesized input
RiplleYang/DenseFusion/datasets/linemod/dataset.py
code served (permissive licence) · get_code("d5126224280f4f78")
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 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 numpy as np
import cv2

# Create a simple binary mask with a rectangle shape
mask = np.zeros((100, 120), dtype=np.float32)
# Draw a white rectangle on the mask
mask[20:80, 30:100] = 1.0

ARGS = {
    "mask": mask
}
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 list, ndim 1, dtype family int — 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
maxOfTwo Ran
ran on a synthesized input
caoquan95/6D-pose-project/lib/evaluate.py
code served (permissive licence) · get_code("b23b47d4dad4cda6")
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)

# Create two small tensors of the same shape
x = torch.randn(2, 4)
y = torch.randn(2, 4)

ARGS = {
    "x": x,
    "y": y
}
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
nValid Ran
ran on a synthesized input
caoquan95/6D-pose-project/lib/evaluate.py
code served (permissive licence) · get_code("46532fb6e38ef70c")
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 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 torch

torch.manual_seed(0)

# The function nValid takes a single tensor argument x
# and counts non-zero elements by converting to float
# We need a tensor with some zero and non-zero values

x = torch.tensor([[1.0, 0.0, 2.0, 3.0],
                   [0.0, 0.0, 4.0, 0.0]], dtype=torch.float32)

ARGS = {
    "x": x
}
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 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
reflection_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RiplleYang/DenseFusion/lib/transformations.py
code served (permissive licence) · get_code("f7f6bfdeee237f86")
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 (4, 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
import math

# Construct arguments for reflection_matrix function
# The function takes:
# - point: should be a vector of length 4 (used as point[:3] for the plane point)
# - normal: should be a vector of length 3+ (used as normal[:3])

point = numpy.array([1.0, 2.0, 3.0, 1.0])
normal = numpy.array([0.5, 0.3, 0.2])

ARGS = {
    "point": point,
    "normal": normal,
}
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 (4, 4) — shape (4, 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
resnet18 Ran
ran on a synthesized input
RiplleYang/DenseFusion/lib/extractors.py
code served (permissive licence) · get_code("05c290474d8f5351")
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 ResNet. 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 math

torch.manual_seed(0)

ARGS = {
    "pretrained": False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran on a synthesized input
RiplleYang/DenseFusion/lib/extractors.py
code served (permissive licence) · get_code("55172193d5361242")
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 ResNet. 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 math

torch.manual_seed(0)

ARGS = {
    "pretrained": False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
setup_logger Ran
ran on a synthesized input
RiplleYang/DenseFusion/lib/utils.py
code served (permissive licence) · get_code("490a3289069aba9a")
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 Logger. 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 logging
import tempfile
import os

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()
log_file_path = os.path.join(temp_dir, "test.log")

ARGS = {
    "logger_name": "test_logger",
    "log_file": log_file_path,
    "level": logging.INFO
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
setup_logger Ran
ran on a synthesized input
caoquan95/6D-pose-project/lib/utils.py
code served (permissive licence) · get_code("5f693bbf3296854b")
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 Logger. 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 logging
import tempfile
import os

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()
log_file_path = os.path.join(temp_dir, "test.log")

ARGS = {
    "logger_name": "test_logger",
    "log_file": log_file_path,
    "level": logging.INFO
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
translation_from_matrix Ran
ran on a synthesized input
RiplleYang/DenseFusion/lib/transformations.py
code served (permissive licence) · get_code("77cb383b0cd2a54e")
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

def translation_matrix(direction):
    """Helper function to create a translation matrix from a direction vector."""
    matrix = numpy.eye(4)
    matrix[:3, 3] = direction
    return matrix

# Create a small translation vector
v0 = numpy.array([0.1, 0.2, 0.3])

# Create a translation matrix (4x4 homogeneous transformation matrix)
matrix = translation_matrix(v0)

ARGS = {
    "matrix": matrix
}
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
translation_matrix Ran
ran on a synthesized input
RiplleYang/DenseFusion/lib/transformations.py
code served (permissive licence) · get_code("edeb1406911ce025")
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 (4, 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

numpy.random.seed(0)

# The function expects a direction vector with at least 3 elements
# It accesses direction[:3] to extract the first 3 components
direction = numpy.random.random(3) - 0.5

ARGS = {
    "direction": direction
}
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 (4, 4) — shape (4, 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
get_bbox Not yet run
unverified (harvested, no recorded run)
cxt98/Densefusion-transparency/tools/eval_ycb.py
code served (permissive licence) · get_code("e1034ecabd32d150")
How it ran

no invocation recorded.

ply_vtx Not yet run
unverified (harvested, no recorded run)
RiplleYang/DenseFusion/datasets/linemod/dataset.py
code served (permissive licence) · get_code("a58ba2b376ee7937")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 8 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 8 later) and 11 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
conv3x3 18 other papers
1 dated earlier, 17 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1905.09646 (2019-05)
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
1910.10750 (2019-10)
6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
and 15 more not named here
reflection_matrix 14 other papers
4 dated earlier, 10 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1803.04996 (2018-03)
Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning
1805.01026 (2018-05)
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
and 11 more not named here
translation_from_matrix 14 other papers
4 dated earlier, 10 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1803.04996 (2018-03)
Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning
1805.01026 (2018-05)
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
and 11 more not named here
translation_matrix 14 other papers
4 dated earlier, 10 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1803.04996 (2018-03)
Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning
1805.01026 (2018-05)
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
and 11 more not named here
resnet18 4 other papers
1 dated earlier, 3 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1910.10750 (2019-10)
6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
2003.00188 (2020-03)
Robust 6D Object Pose Estimation by Learning RGB-D Features
and 1 more not named here
resnet34 4 other papers
1 dated earlier, 3 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1910.10750 (2019-10)
6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints
2003.00188 (2020-03)
Robust 6D Object Pose Estimation by Learning RGB-D Features
and 1 more not named here
get_bbox 1 other paper
1 later
2003.00188 (2020-03)
Robust 6D Object Pose Estimation by Learning RGB-D Features
ply_vtx 1 other paper
1 later
2003.00188 (2020-03)
Robust 6D Object Pose Estimation by Learning RGB-D Features

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

A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image and depth separately or use costly post-processing steps, limiting their performances in highly cluttered scenes and real-time applications. In this work, we present DenseFusion, a generic framework for estimating 6D pose of a set of known objects from RGB-D images. DenseFusion is a heterogeneous architecture that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated. Furthermore, we integrate an end-to-end iterative pose refinement procedure that further improves the pose estimation while achieving near real-time inference. Our experiments show that our method outperforms state-of-the-art approaches in two datasets, YCB-Video and LineMOD. We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose.

For agents

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

get_harvested_code_for_paper("1901.04780")
get_code_for_paper("1901.04780")
have("1901.04780")

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

curl https://syntology.ai/api/ran/1901.04780.json

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

[![Syntology run record](https://syntology.ai/api/ran/1901.04780.svg)](https://syntology.ai/paper/1901.04780)

Connect an agent — have() is free.