SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.01148 · 2021

Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

13 of 13 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; 1 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 10 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/2104.01148.json · badge: /api/ran/2104.01148.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
stelzner/obsurf canonical (classifier label)
classifier basis: census
13 ran · 0 no recorded run
FunctionStatusWhere it lives
build_grid Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/layers.py
code served (permissive licence) · get_code("fbdaf8f5728d098b")
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 4, dtype family float, shape (1, 4, 3, 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

# build_grid takes two parameters:
# 1. resolution: a sequence of integers defining grid dimensions
# 2. with_inverse: a boolean flag

ARGS = {
    "resolution": [4, 3],
    "with_inverse": True
}
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 4, dtype family float, shape (1, 4, 3, 4) — shape (1, 4, 3, 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
check_nan Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/common.py
code served (permissive licence) · get_code("2929fe2070f69fee")
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 int, ndim 0, dtype family int, 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)

# Create a small tensor with some NaN values for testing
x = torch.tensor([[1.0, 2.0, float('nan'), 4.0],
                   [5.0, float('nan'), 7.0, 8.0]])

name = "test_tensor"

ARGS = {
    "x": x,
    "name": name
}
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 int, ndim 0, dtype family int, 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
collect_imports Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/config.py
code served (permissive licence) · get_code("c2fc3eee80f2258b")
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 yaml
import tempfile
import os

# Create temporary YAML files for testing
temp_dir = tempfile.mkdtemp()

# Create an import file
import_file_path = os.path.join(temp_dir, 'import.yaml')
with open(import_file_path, 'w') as f:
    yaml.dump({'imported_key': 'imported_value', 'another_key': 42}, f)

# Create main config dict with nested structures
d = {
    'import': import_file_path,
    'local_key': 'local_value',
    'nested_dict': {
        'inner_key': 'inner_value',
        'import': import_file_path,
        'deep_nested': {
            'deep_key': 'deep_value'
        }
    },
    'simple_value': 123
}

ARGS = {
    'd': d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
compute_adjusted_rand_index Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
stelzner/obsurf/obsurf/common.py
code served (permissive licence) · get_code("76939363c12c55c6")
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 float, 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)

# Construct valid arguments for compute_adjusted_rand_index
# true_mask: Integer Tensor of shape [batch_size, n_true_groups, n_points] with one-hot coded cluster assignments
# pred_mask: Integer Tensor of shape [batch_size, n_pred_groups, n_points] with predicted cluster assignments

batch_size = 2
n_true_groups = 3
n_pred_groups = 4
n_points = 8  # Must be > n_true_groups and > n_pred_groups to avoid the ValueError

# Create true_mask: one-hot coded, shape [batch_size, n_true_groups, n_points]
# Each slice along dimension 1 represents one ground truth group
true_mask = torch.zeros(batch_size, n_true_groups, n_points, dtype=torch.int64)
# For batch 0: assign points to different groups
true_mask[0, 0, :2] = 1  # Group 0 gets points 0-1
true_mask[0, 1, 2:5] = 1  # Group 1 gets points 2-4
true_mask[0, 2, 5:8] = 1  # Group 2 gets points 5-7
# For batch 1: different assignment
true_mask[1, 0, :3] = 1  # Group 0 gets points 0-2
true_mask[1, 1, 3:6] = 1  # Group 1 gets points 3-5
true_mask[1, 2, 6:8] = 1  # Group 2 gets points 6-7

# Create pred_mask: categorical probabilities, shape [batch_size, n_pred_groups, n_points]
# Each entry represents probability of belonging to a predicted group
pred_mask = torch.zeros(batch_size, n_pred_groups, n_points, dtype=torch.float32)
# For batch 0: assign predicted groups
pred_mask[0, 0, :2] = 0.9
pred_mask[0, 1, 2:4] = 0.9
pred_mask[0, 2, 4:6] = 0.9
pred_mask[0, 3, 6:8] = 0.9
# For batch 1: different assignment
pred_mask[1, 0, :2] = 0.9
pred_mask[1, 1, 2:5] = 0.9
pred_mask[1, 2, 5:7] = 0.9
pred_mask[1, 3, 7:8] = 0.9

ARGS = {
    "true_mask": true_mask,
    "pred_mask": pred_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 1, dtype family float, 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
compute_iou Ran
ran, honoured the contract we drafted
stelzner/obsurf/obsurf/common.py
code served (permissive licence) · get_code("0072de07b144b152")
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 (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 numpy as np
import torch

torch.manual_seed(0)

# Create two small occupancy tensors
# occ1: shape (2, 4) - batch of 2, flattened occupancy values of 4
# occ2: shape (2, 4) - same shape for comparison
occ1 = torch.rand(2, 4)
occ2 = torch.rand(2, 4)

ARGS = {
    "occ1": occ1,
    "occ2": occ2,
}
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 1, dtype family float, 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
compute_overshoot Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/model/representations.py
code served (permissive licence) · get_code("1102d4dd638f02d8")
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)

# coords parameter: should be a tensor with shape (batch, ..., 2) or similar
# The function applies torch.abs, torch.clamp, torch.norm with dim=-1
# So we need a tensor where the last dimension represents coordinates
# Let's create a batch of 2D coordinates with shape (2, 4, 2)
coords = torch.randn(2, 4, 2)

ARGS = {
    "coords": coords
}
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
extra_points Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/data.py
code served (permissive licence) · get_code("bfc7cc4e1b6bcaac")
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

ARGS = {
    "min_z": -2.0,
    "max_z": 2.0,
    "points_per_z": 10,
    "xlim": (-4.0, 4.0),
    "ylim": (-4.0, 4.0),
    "num_objs": 11,
    "zthresh": 0.0,
}
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
get_prior Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/model/config.py
code served (permissive licence) · get_code("8957caa92117bc09")
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 Normal. 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.distributions as dist

torch.manual_seed(0)

# Parameters for get_prior
dim = 4
device = torch.device('cpu')

ARGS = {
    'dim': dim,
    'device': device,
}
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 Normal — a Normal output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Normal 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
is_url Ran
ran, violated the contract we drafted
stelzner/obsurf/obsurf/checkpoints.py
code served (permissive licence) · get_code("e39d881796e8d67e")
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 bool, 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 urllib

def is_url(url):
    scheme = urllib.parse.urlparse(url).scheme
    return scheme in ('http', 'https')

ARGS = {
    'url': 'https://example.com'
}
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 bool, 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
load_config Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/config.py
code served (permissive licence) · get_code("5343fa5ff6e12f28")
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 os
import tempfile
import yaml

# Create temporary YAML files for testing
tmpdir = tempfile.mkdtemp()

# Create a simple default config file
default_config = {
    'model': {
        'name': 'default_model',
        'layers': 2
    },
    'training': {
        'epochs': 10,
        'lr': 0.001
    }
}

default_path = os.path.join(tmpdir, 'default_config.yaml')
with open(default_path, 'w') as f:
    yaml.dump(default_config, f)

# Create a special config file that may import from another file
import_config = {
    'shared': {
        'batch_size': 32,
        'seed': 42
    }
}

import_path = os.path.join(tmpdir, 'import_config.yaml')
with open(import_path, 'w') as f:
    yaml.dump(import_config, f)

# Create the main config file that references the import
special_config = {
    'import': import_path,
    'model': {
        'name': 'custom_model',
        'hidden_dim': 128
    },
    'training': {
        'epochs': 20
    }
}

main_path = os.path.join(tmpdir, 'main_config.yaml')
with open(main_path, 'w') as f:
    yaml.dump(special_config, f)

# Define arguments for load_config function
ARGS = {
    'path': main_path,
    'default_path': default_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
make_custom_resnet Ran
ran; our contract draft was wrong, not the code
stelzner/obsurf/obsurf/encoder.py
code served (permissive licence) · get_code("b2298205b9673fe5")
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 CustomResnet. 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
from torchvision import models

torch.manual_seed(0)

ARGS = {
    'arch': 'resnet18',
    'i_dim': 3,
    'c_dim': 128,
    'h_dim': 128,
    'downsample': 0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CustomResnet — a CustomResnet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CustomResnet 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
subsample_clevr Ran
ran, violated the contract we drafted
stelzner/obsurf/obsurf/data.py
code served (permissive licence) · get_code("81fab84438061f33")
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 (64, 64, 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 numpy as np

torch.manual_seed(0)

# The function expects rays to be indexable with tuple slicing
# It applies two operations:
# 1. Spatial crop: rays[29:221, 64:256]
# 2. Subsampling: rays[1::3, 1::3]
# So rays needs to be at least 2D with shape supporting these indices

# Create a rays tensor that's large enough for the cropping and subsampling
# After crop[0][0]:crop[0][1] -> indices 29:221 (192 elements)
# After crop[1][0]:crop[1][1] -> indices 64:256 (192 elements)
# After [1::3, 1::3] subsampling -> 64x64 approximately

# Build something larger to accommodate the operations
rays = torch.randn(300, 350, 4)

ARGS = {
    "rays": rays
}
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 Tensor, ndim 3, dtype family float, shape (64, 64, 4) — shape (64, 64, 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
subsample_clevr_batched Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
stelzner/obsurf/obsurf/data.py
code served (permissive licence) · get_code("e356ea6299306471")
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 4, dtype family float, shape (2, 64, 64, 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)

# The function takes rays and performs:
# 1. Indexing with crop coordinates: rays[:, 29:221, 64:256]
# 2. Strided indexing: rays[:, 1::3, 1::3]
# So rays needs to be a tensor with at least 3 dimensions: (batch, height, width, ...)

# After crop[0]: 221 - 29 = 192
# After crop[1]: 256 - 64 = 192
# After striding by 3 starting at index 1: (192-1)//3 + 1 = 64 for each spatial dim

# Create a small batch of rays with shape (batch, height, width, channels)
rays = torch.randn(2, 256, 300, 4)  # batch=2, height=256, width=300, channels=4

ARGS = {
    "rays": rays
}
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 4, dtype family float, shape (2, 64, 64, 4) — shape (2, 64, 64, 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

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 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
is_url 12 other papers
3 dated earlier, 1 the same month, 8 later
1912.07372 (2019-12)
Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision
2001.05119 (2020-01)
Learning multiview 3D point cloud registration
2003.04618 (2020-03)
Convolutional Occupancy Networks
and 9 more not named here
compute_iou 9 other papers
1 dated earlier, 8 later
2003.04618 (2020-03)
Convolutional Occupancy Networks
2107.01899 (2021-07)
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
2203.13333 (2022-03)
CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
and 6 more not named here

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 ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a different object. A single forward pass of an encoder network outputs a set of latent vectors describing the objects in the scene. These vectors are used independently to condition a NeRF decoder, defining the geometry and appearance of each object. We make learning more computationally efficient by deriving a novel loss, which allows training NeRFs on RGB-D inputs without explicit ray marching. After confirming that the model performs equal or better than state of the art on three 2D image segmentation benchmarks, we apply it to two multi-object 3D datasets: A multiview version of CLEVR, and a novel dataset in which scenes are populated by ShapeNet models. We find that after training ObSuRF on RGB-D views of training scenes, it is capable of not only recovering the 3D geometry of a scene depicted in a single input image, but also to segment it into objects, despite receiving no supervision in that regard.

For agents

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

get_harvested_code_for_paper("2104.01148")
get_code_for_paper("2104.01148")
have("2104.01148")

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

curl https://syntology.ai/api/ran/2104.01148.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.01148.svg)](https://syntology.ai/paper/2104.01148)

Connect an agent — have() is free.