SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.01654 · 2018

Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images

arXiv · PDF · Open in the Atlas

Code that ran

7 of 12 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 6 have no contract verdict; 1 failure of our instrument; 5 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/1804.01654.json · badge: /api/ran/1804.01654.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
nywang16/Pixel2Mesh community (classifier label)
classifier basis not recorded on the link
7 ran · 5 no recorded run
FunctionStatusWhere it lives
camera_info Ran
ran on a synthesized input
nywang16/Pixel2Mesh/GenerateData/3_camera_transform.py
code served (permissive licence) · get_code("d336b18b019a3333")
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

# The function camera_info takes a single parameter 'param'
# which is used as follows:
# - param[0] is converted to radians (theta)
# - param[1] is converted to radians (phi)
# - param[3] is used as a scalar (distance/radius)
# So param needs to be array-like with at least 4 elements

param = np.array([45.0, 30.0, 0.0, 5.0])

ARGS = {
    "param": param
}
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
camera_info Ran
ran on a synthesized input
nywang16/Pixel2Mesh/GenerateData/generate_data.py
code served (permissive licence) · get_code("25de61d1dac76cb8")
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 sklearn.preprocessing

ARGS = {
    "param": np.array([45.0, 30.0, 0.0, 5.0])
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
construct_feed_dict Ran
ran on a synthesized input
nywang16/Pixel2Mesh/p2m/utils.py
code served (permissive licence) · get_code("6f7bdc31cdfaacc3")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Build pkl structure
# pkl[0] = coord (features)
# pkl[1] = support1 (with [1] = adj containing edges[0])
# pkl[2] = support2 (with [1] = adj containing edges[1])
# pkl[3] = support3 (with [1] = adj containing edges[2])
# pkl[4] = pool_idx (list of indices)
# pkl[5] = faces (list of face tensors)
# pkl[7] = lape_idx (list of laplacian indices)

# Create coordinate features (batch_size=2, num_nodes=4, features=3)
coord = torch.randn(2, 4, 3)

# Create support structures for pkl[1], pkl[2], pkl[3]
# Each has structure: [something, adj_matrix]
# adj_matrix[0] is the edge data we extract
support1 = [None, [torch.randn(4, 5)]]  # adj is at index 1, edges[0] is adj[0]
support2 = [None, [torch.randn(4, 6)]]  # adj is at index 1, edges[1] is adj[0]
support3 = [None, [torch.randn(4, 7)]]  # adj is at index 1, edges[2] is adj[0]

# Create pool_idx (list of index tensors)
pool_idx = [torch.tensor([[0, 1], [2, 3]]), torch.tensor([[0, 2], [1, 3]])]

# Create faces (list of face tensors)
faces = [torch.tensor([[0, 1, 2], [1, 2, 3]]), torch.tensor([[0, 1, 3]])]

# Create lape_idx (list of laplacian index tensors)
lape_idx = [torch.tensor([[0, 1], [1, 2]]), torch.tensor([[0, 2], [2, 3]])]

# Assemble pkl
pkl = [
    coord,           # pkl[0]
    support1,        # pkl[1]
    support2,        # pkl[2]
    support3,        # pkl[3]
    pool_idx,        # pkl[4]
    faces,           # pkl[5]
    None,            # pkl[6] (unused)
    lape_idx         # pkl[7]
]

# Build placeholders dict
placeholders = {
    'features': 'feat_placeholder',
    'edges': ['edge_0', 'edge_1', 'edge_2'],
    'faces': ['face_0', 'face_1'],
    'pool_idx': ['pool_0', 'pool_1'],
    'lape_idx': ['lape_0', 'lape_1'],
    'support1': ['sup1_0', 'sup1_1'],
    'support2': ['sup2_0', 'sup2_1'],
    'support3': ['sup3_0', 'sup3_1']
}

ARGS = {
    'pkl': pkl,
    'placeholders': placeholders
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
readFaceInfo Ran
ran on a synthesized input
nywang16/Pixel2Mesh/GenerateData/2_generate_normal.py
code served (permissive licence) · get_code("f292c9b822ce4cfa")
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 4, 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 tempfile
import os

# Create a minimal valid OBJ file for testing
obj_content = """# Simple triangle mesh
v 0.0 0.0 0.0
v 1.0 0.0 0.0
v 0.0 1.0 0.0
v 0.0 0.0 1.0
f 1/1/1 2/2/1 3/3/1
f 1/1/1 2/2/1 4/4/1
"""

# Write to a temporary file
temp_dir = tempfile.gettempdir()
obj_path = os.path.join(temp_dir, "test_mesh.obj")
with open(obj_path, 'w') as f:
    f.write(obj_content)

ARGS = {
    "obj_path": obj_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, ndim 4, 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
unit Ran
ran on a synthesized input
nywang16/Pixel2Mesh/p2m/losses.py
code served (permissive licence) · get_code("ecfd96810a9fa29d")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

def unit(tensor):
    return tf.nn.l2_normalize(tensor, dim=1)

# Create a small tensor with shape (2, 4) - batch size 2, dimension 4
tensor_np = np.array([[1.0, 2.0, 3.0, 4.0],
                       [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)
tensor = tf.constant(tensor_np)

ARGS = {
    "tensor": tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
unit Ran
ran on a synthesized input
nywang16/Pixel2Mesh/GenerateData/2_generate_normal.py
code served (permissive licence) · get_code("a688e7eaa817d5c2")
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

# The function unit() takes a vector v and normalizes it.
# It computes the norm using np.linalg.norm and divides by it (if non-zero).
# So v should be a numpy array.

# Create a small test vector
v = np.array([3.0, 4.0, 0.0, 0.0])

ARGS = {
    "v": v
}
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
zeros Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nywang16/Pixel2Mesh/p2m/inits.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from flyingdoog/PTDNet, is pointer only (licence: NONE) · get_code("b190ef9c60b2629a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from flyingdoog/PTDNet, and GitHub detected no licence in that repository when it was checked. 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.

generate_normal Not yet run
unverified (harvested, no recorded run)
nywang16/Pixel2Mesh/GenerateData/2_generate_normal.py
code served (permissive licence) · get_code("f9a49c20298b14d3")
How it ran

no invocation recorded.

glorot Not yet run
unverified (harvested, no recorded run)
nywang16/Pixel2Mesh/p2m/inits.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from nju-websoft/OpenEA, is pointer only (licence: GPL-3.0) · get_code("1b491f3f784b7cb0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from nju-websoft/OpenEA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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. No invocation recorded.

laplace_coord Not yet run
unverified (harvested, no recorded run)
nywang16/Pixel2Mesh/p2m/losses.py
code served (permissive licence) · get_code("c2a076abe0d081bc")
How it ran

no invocation recorded.

laplace_loss Not yet run
unverified (harvested, no recorded run)
nywang16/Pixel2Mesh/p2m/losses.py
code served (permissive licence) · get_code("e8df99f2ace67cd4")
How it ran

no invocation recorded.

uniform Not yet run
unverified (harvested, no recorded run)
nywang16/Pixel2Mesh/p2m/inits.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from flyingdoog/PTDNet, is pointer only (licence: NONE) · get_code("b0d1b78daecde7e9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from flyingdoog/PTDNet, and GitHub detected no licence in that repository when it was checked. 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 5 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
zeros 18 other papers
1 dated earlier, 1 the same month, 16 later
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1811.02061 (2018-11)
A Recurrent Graph Neural Network for Multi-Relational Data
and 15 more not named here
uniform 17 other papers
1 dated earlier, 1 the same month, 15 later
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1811.02061 (2018-11)
A Recurrent Graph Neural Network for Multi-Relational Data
and 14 more not named here
glorot 16 other papers
1 dated earlier, 1 the same month, 14 later
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1804.00823 (2018-04)
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
1811.02061 (2018-11)
A Recurrent Graph Neural Network for Multi-Relational Data
and 13 more not named here
laplace_coord 1 other paper
1 later
1908.01491 (2019-08)
Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation
unit 1 other paper
1 later
2008.05742 (2020-08)
SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images

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 propose an end-to-end deep learning architecture that produces a 3D shape in triangular mesh from a single color image. Limited by the nature of deep neural network, previous methods usually represent a 3D shape in volume or point cloud, and it is non-trivial to convert them to the more ready-to-use mesh model. Unlike the existing methods, our network represents 3D mesh in a graph-based convolutional neural network and produces correct geometry by progressively deforming an ellipsoid, leveraging perceptual features extracted from the input image. We adopt a coarse-to-fine strategy to make the whole deformation procedure stable, and define various of mesh related losses to capture properties of different levels to guarantee visually appealing and physically accurate 3D geometry. Extensive experiments show that our method not only qualitatively produces mesh model with better details, but also achieves higher 3D shape estimation accuracy compared to the state-of-the-art.

For agents

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

get_harvested_code_for_paper("1804.01654")
get_code_for_paper("1804.01654")
have("1804.01654")

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

curl https://syntology.ai/api/ran/1804.01654.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.01654.svg)](https://syntology.ai/paper/1804.01654)

Connect an agent — have() is free.