SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.00614 · 2020

Articulation-aware Canonical Surface Mapping

arXiv · PDF · Open in the Atlas

Code that ran

14 of 17 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; 2 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 0 failures of our instrument; 3 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/2004.00614.json · badge: /api/ran/2004.00614.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
nileshkulkarni/acsm community (classifier label)
classifier basis not recorded on the link
14 ran · 3 no recorded run
FunctionStatusWhere it lives
camPosToQuaternion Ran
ran, honoured the contract we drafted
nileshkulkarni/acsm/acsm/renderer/render_model_ortho_views.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sarthaksharma13/RenderForCNN_KeypointGeneration, is pointer only (licence: NOASSERTION) · get_code("478f5c0f1d3df811")
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 sarthaksharma13/RenderForCNN_KeypointGeneration, 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.

camRotQuaternion Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/renderer/render_model_ortho_views.py
code served (permissive licence) · get_code("916c004f7fb4c87c")
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 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 math

def camRotQuaternion(cx, cy, cz, theta):
    theta = theta / 180.0 * math.pi
    camDist = math.sqrt(cx * cx + cy * cy + cz * cz)
    cx = -cx / camDist
    cy = -cy / camDist
    cz = -cz / camDist
    q1 = math.cos(theta * 0.5)
    q2 = -cx * math.sin(theta * 0.5)
    q3 = -cy * math.sin(theta * 0.5)
    q4 = -cz * math.sin(theta * 0.5)
    return (q1, q2, q3, q4)

ARGS = {
    "cx": 1.0,
    "cy": 2.0,
    "cz": 3.0,
    "theta": 45.0
}
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 tuple, ndim 1, 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
ck_at_interval Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/benchmark/pck_eval.py
code served (permissive licence) · get_code("e9a74ce31735f8a9")
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 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

# Construct arguments for ck_at_interval
intervals = [0.1, 0.5, 1.0, 2.0]
error = np.array([0.05, 0.3, 0.8, 1.5])

ARGS = {
    "intervals": intervals,
    "error": error
}
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 list, ndim 2, 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
code_loss Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/de_loss_utils.py
code served (permissive licence) · get_code("f610cc3cbbf5fe56")
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 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 torch
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Define a minimal options class with required attributes
class Opts:
    def __init__(self):
        self.output_img_size = 4
        self.nll_loss_wt = 1.0
        self.exp_loss_wt = 1.0

# Set dimensions
bsize = 2
feat_dim = 4
H = 3
W = 5

# Create codes_pred dict with required tensors
codes_pred = {
    'feat_u': torch.randn(bsize, feat_dim, H, W),
    'feat_v': torch.randn(bsize, feat_dim, H, W),
}

# Create codes_gt dict with required tensors
codes_gt = {
    'guv_adj': torch.rand(bsize, H, W, 2) * 2 - 1,  # Normalized coordinates for grid_sample
    'downsample_grid': torch.rand(bsize, 1, H * W, 2) * 2 - 1,  # Normalized coordinates
    'ds_mask_u': torch.randint(0, 2, (bsize, H * W)).float(),
    'ds_mask_v': torch.randint(0, 2, (bsize, 1, H * W, 1)).float(),
}

# Create opts instance
opts = Opts()

ARGS = {
    'codes_pred': codes_pred,
    'codes_gt': codes_gt,
    'opts': opts,
}
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 1, 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
conv2d Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/de_net.py
code served (permissive licence) · get_code("559f5c4d23de6d99")
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 Sequential. 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)

ARGS = {
    "in_planes": 3,
    "out_planes": 16,
    "kernel_size": 3,
    "stride": 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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
depth_loss_fn Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/loss_utils.py
code served (permissive licence) · get_code("7967131366de699b")
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, 1) 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)

# Construct arguments for depth_loss_fn
# The function expects:
# - depth_render: tensor that will be compared against depth_pred
# - depth_pred: predicted depth tensor
# - mask: binary mask tensor for weighting

batch_size = 2
height = 4
width = 3

depth_render = torch.randn(batch_size, 1, height, width)
depth_pred = torch.randn(batch_size, 1, height, width)
mask = torch.ones(batch_size, 1, height, width)

ARGS = {
    "depth_render": depth_render,
    "depth_pred": depth_pred,
    "mask": mask,
}
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, 1) — shape (2, 1) 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
depth_loss_fn_vis Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/loss_utils.py
code served (permissive licence) · get_code("fa754d842092d235")
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 3, dtype family float, shape (2, 4, 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

torch.manual_seed(0)

# Create small tensors for depth_loss_fn_vis
# The function expects:
# - depth_render: tensor of rendered depths
# - depth_pred: tensor of predicted depths
# - mask: binary mask tensor

batch_size = 2
height = 4
width = 3

depth_render = torch.randn(batch_size, height, width)
depth_pred = torch.randn(batch_size, height, width)
mask = torch.randint(0, 2, (batch_size, height, width)).float()

ARGS = {
    "depth_render": depth_render,
    "depth_pred": depth_pred,
    "mask": mask,
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 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
mask_loss_fn Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/loss_utils.py
code served (permissive licence) · get_code("338418906f6b74b4")
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)

# mask_loss_fn expects:
# - mask_pred: a tensor that will be subtracted from mask_gt and reshaped
# - mask_gt: a tensor with same shape as mask_pred
# The function reshapes to (shape[0], shape[1], -1), so we need at least 3 dimensions
# Using shape (2, 4, 3, 5) to have distinct sizes: batch=2, channels=4, height=3, width=5

mask_pred = torch.randn(2, 4, 3, 5)
mask_gt = torch.randn(2, 4, 3, 5)

ARGS = {
    "mask_pred": mask_pred,
    "mask_gt": mask_gt,
}
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
pck_at_intervals Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/benchmark/pck_eval.py
code served (permissive licence) · get_code("283e549766187046")
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

# Create small error array with distinct values
error = np.array([0.5, 1.2, 0.8, 1.5, 0.3, 2.1, 0.9, 1.8])

# Create intervals to evaluate PCK at
intervals = [0.5, 1.0, 1.5, 2.0]

ARGS = {
    "intervals": intervals,
    "error": error,
}
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 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
quaternionFromYawPitchRoll Ran
ran, honoured the contract we drafted
nileshkulkarni/acsm/acsm/renderer/render_model_ortho_views.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sarthaksharma13/RenderForCNN_KeypointGeneration, is pointer only (licence: NOASSERTION) · get_code("02fcb6803abcb05d")
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 sarthaksharma13/RenderForCNN_KeypointGeneration, 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.

ravel_coordinates_image Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/net_blocks.py
code served (permissive licence) · get_code("f4dae52c3c6ea0ac")
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 1, dtype family int, shape (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 torch

torch.manual_seed(0)

# Create a tiny index tensor with shape (batch_size=2, num_dims=3)
# The index contains coordinate indices into each dimension
index = torch.tensor([
    [1, 0, 2],
    [0, 1, 1]
], dtype=torch.long)

# Create a shape tuple representing image dimensions
# shape should have 3 elements to match the index columns
shape = (5, 4, 3)

ARGS = {
    "index": index,
    "shape": shape
}
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 1, dtype family int, shape (2,) — shape (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
ravel_index_pytorch Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/net_blocks.py
code served (permissive licence) · get_code("67351b97803513ef")
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 1, dtype family int, shape (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 torch

torch.manual_seed(0)

# Create a small index tensor with shape (batch_size=2, num_dims=4)
# Each row contains indices into the corresponding dimension
index = torch.tensor([
    [0, 1, 2, 3],
    [1, 0, 1, 2]
], dtype=torch.long)

# Create a shape tuple representing the dimensions of the multi-dimensional array
# Using distinct sizes: 5, 4, 3, 2
shape = (5, 4, 3, 2)

ARGS = {
    "index": index,
    "shape": shape
}
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 1, dtype family int, shape (2,) — shape (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
remove_nans Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/benchmark/pck_eval.py
code served (permissive licence) · get_code("63d8b60083ae8c04")
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 remove_nans takes a numpy array x and removes NaN values
# It uses np.isnan() to create a boolean mask and fancy indexing to filter

# Create a small numpy array with some NaN values
x = np.array([1.0, np.nan, 3.0, np.nan, 5.0, 2.0])

ARGS = {
    "x": x
}
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
unravel_coordinates_image Ran
ran on a synthesized input
nileshkulkarni/acsm/acsm/nnutils/net_blocks.py
code served (permissive licence) · get_code("f84e233547584167")
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 int, shape (2, 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

torch.manual_seed(0)

# Create a small rindex tensor with batch size 2
# rindex should contain flat indices into a multi-dimensional array
rindex = torch.tensor([5, 11], dtype=torch.long)

# Create a shape tuple for the multi-dimensional array
# shape should have at least 3 dimensions (since the function accesses indices 0, 1, 2)
shape = (4, 3, 5)

ARGS = {
    "rindex": rindex,
    "shape": shape,
}
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 int, shape (2, 3) — shape (2, 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
inst_bench_evaluate Not yet run
unverified (harvested, no recorded run)
nileshkulkarni/acsm/acsm/benchmark/evaluate_pr.py
code served (permissive licence) · get_code("b1e594c7cca4ac5c")
How it ran

no invocation recorded.

load_active_parts Not yet run
unverified (harvested, no recorded run)
nileshkulkarni/acsm/acsm/nnutils/model_utils.py
code served (permissive licence) · get_code("4d48c5e8db68bd8c")
How it ran

no invocation recorded.

load_template_shapes Not yet run
unverified (harvested, no recorded run)
nileshkulkarni/acsm/acsm/nnutils/model_utils.py
code served (permissive licence) · get_code("c2ef71b3326d1864")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 15 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
camPosToQuaternion 1 other paper
1 dated earlier
1505.05641 (2015-05)
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
quaternionFromYawPitchRoll 1 other paper
1 dated earlier
1505.05641 (2015-05)
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views

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

We tackle the tasks of: 1) predicting a Canonical Surface Mapping (CSM) that indicates the mapping from 2D pixels to corresponding points on a canonical template shape, and 2) inferring the articulation and pose of the template corresponding to the input image. While previous approaches rely on keypoint supervision for learning, we present an approach that can learn without such annotations. Our key insight is that these tasks are geometrically related, and we can obtain supervisory signal via enforcing consistency among the predictions. We present results across a diverse set of animal object categories, showing that our method can learn articulation and CSM prediction from image collections using only foreground mask labels for training. We empirically show that allowing articulation helps learn more accurate CSM prediction, and that enforcing the consistency with predicted CSM is similarly critical for learning meaningful articulation.

For agents

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

get_harvested_code_for_paper("2004.00614")
get_code_for_paper("2004.00614")
have("2004.00614")

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

curl https://syntology.ai/api/ran/2004.00614.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.00614.svg)](https://syntology.ai/paper/2004.00614)

Connect an agent — have() is free.