SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.07433 · 2019

Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation

arXiv · PDF · Open in the Atlas

Code that ran

4 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 4 have no contract verdict; 0 failures of our instrument; 4 no recorded run), measured 2026-11-21; 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/1908.07433.json · badge: /api/ran/1908.07433.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
hz-ants/Pix2Pose community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
kirumang/Pix2Pose community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_rotation_from_vertex Ran
ran on a synthesized input
hz-ants/Pix2Pose/rendering/utils.py
code served (permissive licence) · get_code("f1f755c2a962bfe2")
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 (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
from scipy.linalg import expm, norm

# The function compute_rotation_from_vertex takes a vertex parameter
# which should be a 3D point (array-like with 3 elements)
# The function uses:
# - vertex[0], vertex[1], vertex[2] (indexing)
# - norm(vertex) (scipy.linalg.norm)
# - np.cross() operations
# - array slicing and arithmetic

# Create a valid vertex (3D point)
vertex = np.array([1.0, 2.0, 3.0])

ARGS = {
    "vertex": vertex
}
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 ndarray, ndim 2, dtype family float, shape (3, 3) — shape (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
conv_block Ran
ran on a synthesized input
kirumang/Pix2Pose/pix2pose_model/resnet50_mod.py
code served (permissive licence) · get_code("0c20710ab8a2abc9")
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 KerasTensor. 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 numpy as np
from keras import backend as K
from keras.layers import Input

# Set image data format to channels_last for consistent behavior
K.set_image_data_format('channels_last')

# Create a small input tensor with shape (batch, height, width, channels)
# batch=2, height=4, width=4, channels=3
input_tensor = Input(shape=(4, 4, 3))

ARGS = {
    'input_tensor': input_tensor,
    'kernel_size': 3,
    'filters': [64, 64, 256],
    'stage': 2,
    'block': 'a',
    'strides': (2, 2)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor output has no array shape of its own; none is 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
getXYZ Ran
ran on a synthesized input
kirumang/Pix2Pose/pix2pose_util/common_util.py
code served (permissive licence) · get_code("56ef64fd9c7a6e8f")
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

# Create a small depth map (height=4, width=3)
depth = np.random.rand(4, 3) * 10.0  # depth values between 0-10

# Camera intrinsics
fx = 500.0
fy = 500.0
cx = 1.5
cy = 2.0

# Default bbox (shape [1] means no bounding box filtering)
bbox = np.array([0])

ARGS = {
    "depth": depth,
    "fx": fx,
    "fy": fy,
    "cx": cx,
    "cy": cy,
    "bbox": bbox,
}
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
singleton Ran
ran on a synthesized input
hz-ants/Pix2Pose/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
draw_detections_2D Not yet run
unverified (harvested, no recorded run)
hz-ants/Pix2Pose/rendering/utils.py
code served (permissive licence) · get_code("58e205d70619d7b4")
How it ran

no invocation recorded.

get_bbox_from_mask Not yet run
unverified (harvested, no recorded run)
hz-ants/Pix2Pose/pix2pose_util/common_util.py
code served (permissive licence) · get_code("2a1a7f9181849be6")
How it ran

no invocation recorded.

get_normal Not yet run
unverified (harvested, no recorded run)
kirumang/Pix2Pose/pix2pose_util/common_util.py
code served (permissive licence) · get_code("d73753b0d8a243a5")
How it ran

no invocation recorded.

identity_block Not yet run
unverified (harvested, no recorded run)
kirumang/Pix2Pose/pix2pose_model/resnet50_mod.py
code served (permissive licence) · get_code("4709da86c7cc71fd")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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
singleton 1 other paper
1 dated earlier
1810.03065 (2018-10)
Deep Model-Based 6D Pose Refinement in RGB

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Estimating the 6D pose of objects using only RGB images remains challenging because of problems such as occlusion and symmetries. It is also difficult to construct 3D models with precise texture without expert knowledge or specialized scanning devices. To address these problems, we propose a novel pose estimation method, Pix2Pose, that predicts the 3D coordinates of each object pixel without textured models. An auto-encoder architecture is designed to estimate the 3D coordinates and expected errors per pixel. These pixel-wise predictions are then used in multiple stages to form 2D-3D correspondences to directly compute poses with the PnP algorithm with RANSAC iterations. Our method is robust to occlusion by leveraging recent achievements in generative adversarial training to precisely recover occluded parts. Furthermore, a novel loss function, the transformer loss, is proposed to handle symmetric objects by guiding predictions to the closest symmetric pose. Evaluations on three different benchmark datasets containing symmetric and occluded objects show our method outperforms the state of the art using only RGB images.

For agents

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

get_harvested_code_for_paper("1908.07433")
get_code_for_paper("1908.07433")
have("1908.07433")

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

curl https://syntology.ai/api/ran/1908.07433.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.07433.svg)](https://syntology.ai/paper/1908.07433)

Connect an agent — have() is free.