SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08454 · 2020

Shape Prior Deformation for Categorical 6D Object Pose and Size 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; 0 honoured the contract we drafted, 1 violated it and 2 have 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/2007.08454.json · badge: /api/ran/2007.08454.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
mentian/object-deformnet canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
gritYCDA/shape_deform community (classifier label)
classifier basis: plan_row
3 ran · 0 no recorded run
FunctionStatusWhere it lives
backproject Ran
ran on a synthesized input
mentian/object-deformnet/lib/align.py
code served (permissive licence) · get_code("175a12292e74a5a4")
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. 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

# Create a small depth map (height=3, width=4)
depth = np.array([
    [0.5, 1.0, 1.5, 0.0],
    [0.8, 1.2, 0.0, 2.0],
    [1.1, 0.9, 1.3, 1.6]
], dtype=np.float32)

# Create intrinsic camera matrix (3x3)
# cam_fx, cam_fy, cam_cx, cam_cy
intrinsics = np.array([
    [500.0, 0.0, 2.0],
    [0.0, 500.0, 1.5],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

# Create instance mask (height=3, width=4)
instance_mask = np.array([
    [True, True, False, False],
    [True, True, False, True],
    [True, True, True, True]
], dtype=bool)

ARGS = {
    "depth": depth,
    "intrinsics": intrinsics,
    "instance_mask": instance_mask
}
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 tuple — a tuple 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
gritYCDA/shape_deform/lib/pspnet.py
code served (permissive licence) · get_code("a3fc43aa1154384a")
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 Conv2d. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'in_planes': 3,
    'out_planes': 64,
    'stride': 1,
    'dilation': 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
estimateSimilarityTransform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gritYCDA/shape_deform/lib/align.py
code served (permissive licence) · get_code("7065cc05bc9b5e3f")
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. 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

# Create small sample point clouds
# Source: 10 points in 3D
np.random.seed(0)
source = np.random.randn(10, 3).astype(np.float64)

# Target: Apply a known similarity transform to source
rotation_matrix = np.array([
    [0.866, -0.5, 0.0],
    [0.5, 0.866, 0.0],
    [0.0, 0.0, 1.0]
], dtype=np.float64)
scale = 1.5
translation = np.array([1.0, 2.0, 3.0], dtype=np.float64)

target = scale * (source @ rotation_matrix.T) + translation

ARGS = {
    "source": source,
    "target": target,
    "verbose": False
}
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 tuple — a tuple 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
estimateSimilarityUmeyama Ran
ran; our contract draft was wrong, not the code
gritYCDA/shape_deform/lib/align.py
code served (permissive licence) · get_code("88e63c6b872d1923")
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. 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

# Create small sample point clouds in homogeneous coordinates
# Shape should be (4, nPoints) where first 3 rows are 3D points, last row is 1s
nPoints = 5

# Source points in homogeneous coordinates (4 x nPoints)
SourceHom = np.random.randn(4, nPoints)
SourceHom[3, :] = 1.0  # Homogeneous coordinate

# Target points in homogeneous coordinates (4 x nPoints)
# Create a transformed version of source to ensure valid input
TargetHom = np.random.randn(4, nPoints)
TargetHom[3, :] = 1.0  # Homogeneous coordinate

ARGS = {
    "SourceHom": SourceHom,
    "TargetHom": TargetHom
}
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 tuple — a tuple 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
load_obj Ran
ran; our contract draft was wrong, not the code
mentian/object-deformnet/lib/utils.py
code served (permissive licence) · get_code("1f5e0fafdbfd5166")
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. 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
import tempfile
import os

# Create a temporary OBJ file for testing
temp_dir = tempfile.mkdtemp()
obj_file_path = os.path.join(temp_dir, "test.obj")

# Write a simple OBJ file with vertices and faces
obj_content = """# Simple test cube
v 0.0 0.0 0.0
v 1.0 0.0 0.0
v 1.0 1.0 0.0
v 0.0 1.0 0.0
v 0.0 0.0 1.0
v 1.0 0.0 1.0
v 1.0 1.0 1.0
v 0.0 1.0 1.0
f 1 2 3
f 1 3 4
f 5 6 7
f 5 7 8
"""

with open(obj_file_path, 'w') as f:
    f.write(obj_content)

ARGS = {
    'path_to_file': obj_file_path
}
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 tuple — a tuple 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
process_data Ran
ran on a synthesized input
mentian/object-deformnet/preprocess/pose_data.py
code served (permissive licence) · get_code("965fc9f134ceab2a")
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. 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 cv2
import numpy as np
import tempfile
import os

# Create temporary directory for test files
tmpdir = tempfile.mkdtemp()

# Create a minimal valid image path base
img_path = os.path.join(tmpdir, "test_image")

# Create mask image: 480x640 with instance IDs and background (255)
mask_img = np.zeros((480, 640, 3), dtype=np.uint8)
# Set channel 2 (B channel) with mask data
mask_img[:100, :100, 2] = 1      # instance 1
mask_img[100:200, 100:200, 2] = 2  # instance 2
mask_img[200:, 200:, 2] = 255    # background
cv2.imwrite(img_path + '_mask.png', mask_img)

# Create coordinate map image
coord_img = np.random.randint(0, 255, (480, 640, 3), dtype=np.uint8)
cv2.imwrite(img_path + '_coord.png', coord_img)

# Create depth map
depth = np.ones((480, 640), dtype=np.float32)
depth[:50, :50] = 0  # Some zero depth values
depth[100:150, 100:150] = 5.0  # Valid depth for instance 2

# Create metadata file
meta_content = """1 1 model_1
2 2 model_2
3 0 model_3
"""
with open(img_path + '_meta.txt', 'w') as f:
    f.write(meta_content)

ARGS = {
    'img_path': img_path,
    'depth': depth
}
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 tuple — a tuple 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
random_point Ran
ran, violated the contract we drafted
mentian/object-deformnet/lib/utils.py
code served (permissive licence) · get_code("c21f8ac3fafbb5e2")
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

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

# face_vertices should be a numpy array with shape (3, 3) representing 3 vertices in 3D space
# The function expects face_vertices[0, :], face_vertices[1, :], face_vertices[2, :] to be individual vertex positions
face_vertices = np.array([
    [0.0, 0.0, 0.0],      # vertex 0
    [1.0, 0.0, 0.0],      # vertex 1
    [0.0, 1.0, 0.0]       # vertex 2
], dtype=np.float32)

ARGS = {
    "face_vertices": face_vertices
}
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
setup_logger Ran
ran; our contract draft was wrong, not the code
mentian/object-deformnet/lib/utils.py
code served (permissive licence) · get_code("8c1b06b5e547f722")
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

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, 6 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 6 later) and 2 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
6 dated earlier, 12 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1901.04780 (2019-01)
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
1905.09646 (2019-05)
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
and 15 more not named here
load_obj 2 other papers
2 later
aaai_20104 (2022 (year only))
Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation
2309.10255 (2023-09)
RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery
random_point 2 other papers
2 later
aaai_20104 (2022 (year only))
Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation
2309.10255 (2023-09)
RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery
setup_logger 2 other papers
2 later
aaai_20104 (2022 (year only))
Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation
2309.10255 (2023-09)
RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery
estimateSimilarityTransform 1 other paper
1 later
2309.10255 (2023-09)
RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery
estimateSimilarityUmeyama 1 other paper
1 later
2309.10255 (2023-09)
RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery

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 learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. To handle the intra-class shape variation, we propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior. Additionally, our network infers the dense correspondences between the depth observation of the object instance and the reconstructed 3D model to jointly estimate the 6D object pose and size. We design an autoencoder that trains on a collection of object models and compute the mean latent embedding for each category to learn the categorical shape priors. Extensive experiments on both synthetic and real-world datasets demonstrate that our approach significantly outperforms the state of the art. Our code is available at https://github.com/mentian/object-deformnet.

For agents

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

get_harvested_code_for_paper("2007.08454")
get_code_for_paper("2007.08454")
have("2007.08454")

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

curl https://syntology.ai/api/ran/2007.08454.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.08454.svg)](https://syntology.ai/paper/2007.08454)

Connect an agent — have() is free.