SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16832 · ECCV · 2022

Point Scene Understanding via Disentangled Instance Mesh Reconstruction

Jiaxiang Tang, Xiaokang Chen, Jingbo Wang, Gang Zeng

arXiv · PDF · Open in the Atlas

Code that ran

16 of 16 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, 0 violated it and 11 have no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2203.16832.json · badge: /api/ran/2203.16832.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
ashawkey/dimr canonical (classifier label)
classifier basis not recorded on the link
16 ran · 0 no recorded run
FunctionStatusWhere it lives
chamfer_distance Ran
ran on a synthesized input
ashawkey/dimr/evaluation/cd/metrics.py
code served (permissive licence) · get_code("db0ecf50d179a176")
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 float64, ndim 0, 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

np.random.seed(0)

# Create two point clouds with distinct shapes for clarity
# x: 5 points in 3D space
x = np.random.randn(5, 3).astype(np.float32)

# y: 4 points in 3D space (different number of points)
y = np.random.randn(4, 3).astype(np.float32)

ARGS = {
    'x': x,
    'y': y,
    'metric': 'l2',
    'direction': 'bi'
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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_mesh_iou Ran
ran on a synthesized input
ashawkey/dimr/evaluation/iou/metrics.py
code served (permissive licence) · get_code("d29b83a50ca7413d")
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 float, 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 numpy as np

class MockVoxelGrid:
    def __init__(self, num_internal=5, num_surface=8, has_internal=True):
        self.filled_count = num_internal if has_internal else 0
        # Create distinct point clouds
        if has_internal:
            self.points = np.random.rand(num_internal + num_surface, 3).astype(np.float32)
        else:
            self.points = np.random.rand(num_surface, 3).astype(np.float32)
    
    def is_filled(self, points):
        # Return a boolean array indicating which points are filled
        # Simple heuristic: points with sum > 1.0 are considered filled
        return np.sum(points, axis=1) > 1.0

# Create first voxel pair (internal, surface)
voxel1_internal = MockVoxelGrid(num_internal=6, num_surface=8, has_internal=True)
voxel1_surface = MockVoxelGrid(num_internal=0, num_surface=10, has_internal=False)
voxel1 = (voxel1_internal, voxel1_surface)

# Create second voxel pair (internal, surface)
voxel2_internal = MockVoxelGrid(num_internal=5, num_surface=7, has_internal=True)
voxel2_surface = MockVoxelGrid(num_internal=0, num_surface=9, has_internal=False)
voxel2 = (voxel2_internal, voxel2_surface)

ARGS = {
    'voxel1': voxel1,
    'voxel2': voxel2
}
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 float, 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
get_coords_color Ran
ran on a synthesized input
ashawkey/dimr/util/visualize.py
code served (permissive licence) · get_code("308f1be6b6077572")
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 3, 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 os
import tempfile
from unittest.mock import Mock, patch

# Create a mock options object with all required attributes
class MockOpt:
    def __init__(self):
        self.room_name = 'test_room'
        self.room_split = 'val'
        self.task = 'semantic_gt'
        self.result_root = './results'

# Create temporary directory structure and mock data files
def create_mock_data():
    opt = MockOpt()
    
    # Create mock npz file with required arrays
    mock_data = {
        'mesh_vertices': np.random.rand(100, 6).astype(np.float32),
        'instance_labels': np.random.randint(0, 10, 100).astype(np.int32),
        'semantic_labels': np.random.randint(0, 25, 100).astype(np.int32)
    }
    
    # Patch np.load to return mock data
    def mock_load(path):
        if path.endswith('data.npz'):
            class MockNpz:
                def __init__(self, data):
                    self.data = data
                def __getitem__(self, key):
                    return self.data[key]
            return MockNpz(mock_data)
        elif path.endswith('.npy'):
            return np.random.rand(100).astype(np.float32)
        return None
    
    return opt, mock_load

opt, mock_load_func = create_mock_data()

# Patch os.path.join and os.path.isfile to handle mock paths
original_join = os.path.join
original_isfile = os.path.isfile

def mock_join(*args):
    return '/'.join(args)

def mock_isfile(path):
    return True

# Create ARGS dictionary with patched functions
ARGS = {
    'opt': opt
}

# Apply patches at module level for the function to work
import builtins
_original_load = np.load

def patched_load(path, *args, **kwargs):
    if 'data.npz' in path:
        class MockNpz:
            def __init__(self):
                self.data = {
                    'mesh_vertices': np.random.rand(100, 6).astype(np.float32),
                    'instance_labels': np.random.randint(0, 10, 100).astype(np.int32),
                    'semantic_labels': np.random.randint(0, 25, 100).astype(np.int32)
                }
            def __getitem__(self, key):
                return self.data[key]
        return MockNpz()
    else:
        return np.random.rand(100).astype(np.float32)

np.load = patched_load
os.path.join = mock_join
os.path.isfile = mock_isfile

ARGS = {
    'opt': opt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, 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
get_instances Ran
ran on a synthesized input
ashawkey/dimr/util/utils_3d.py
code served (permissive licence) · get_code("4e07440bd3364b80")
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 numpy as np

# Create mesh vertex instances array where each element is an instance ID
# Instance IDs are formatted as label_id * 1000 + instance_offset
# For example: label_id=2 with instance_offset=5 gives instance_id=2005
ids = np.array([0, 2005, 2005, 2008, 3012, 3012, 3012, 0], dtype=np.int32)

# Class IDs that we're interested in (labels 2 and 3)
class_ids = [2, 3]

# Class labels (human-readable names for the classes)
class_labels = ['wall', 'floor']

# Mapping from label_id to label name
id2label = {
    2: 'wall',
    3: 'floor'
}

ARGS = {
    'ids': ids,
    'class_ids': class_ids,
    'class_labels': class_labels,
    'id2label': id2label
}
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 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
get_iou Ran
ran on a synthesized input
ashawkey/dimr/evaluation/iou/metrics.py
code served (permissive licence) · get_code("e3928e46e3ea2137")
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 float64, ndim 0, 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 two 6D bounding boxes in min-max format
# Format: [min_x, min_y, min_z, max_x, max_y, max_z]
box_a = np.array([0.0, 0.0, 0.0, 2.0, 2.0, 2.0])
box_b = np.array([1.0, 1.0, 1.0, 3.0, 3.0, 3.0])

ARGS = {
    "box_a": box_a,
    "box_b": box_b,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
huber_loss Ran
ran; our contract draft was wrong, not the code
ashawkey/dimr/model/rfs.py
code served (permissive licence) · get_code("3e37ecc673899eb2")
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)

# The function takes an error tensor and a delta scalar
# It applies the Huber loss formula element-wise on the error tensor
# Parameters:
# - error: a tensor of prediction errors (pred - gt)
# - delta: a scalar threshold parameter (default 1.0)

error = torch.randn(2, 4)  # Small batch of errors
delta = 1.0

ARGS = {
    "error": error,
    "delta": delta,
}
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
intersectionAndUnion Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ashawkey/dimr/util/utils.py
code served (permissive licence) · get_code("a75f890684e211c9")
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 2, dtype family int; 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 numpy as np

torch.manual_seed(0)

# Create small numpy arrays for output and target
# The function expects them to have the same shape
# Using 1D arrays for simplicity
output = np.array([0, 1, 2, 1, 0, 255, 2], dtype=np.int64)
target = np.array([0, 1, 1, 1, 3, 255, 2], dtype=np.int64)

# K is the number of classes (must be >= max value in output/target excluding ignore_index)
K = 4

# ignore_index is the value to ignore (default 255)
ignore_index = 255

ARGS = {
    "output": output,
    "target": target,
    "K": K,
    "ignore_index": ignore_index
}
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 tuple, ndim 2, dtype family int — 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
is_power2 Ran
ran on a synthesized input
ashawkey/dimr/util/utils.py
code served (permissive licence) · get_code("acda2d896528f730")
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 torch

torch.manual_seed(0)

def is_power2(num):
    return num != 0 and num & num - 1 == 0

ARGS = {
    "num": 8
}
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 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_ids Ran
ran, honoured the contract we drafted
ashawkey/dimr/util/utils_3d.py
code served (permissive licence) · get_code("14f23821245c2d26")
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 int, 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 json
import numpy as np
import tempfile
import os

# Create a temporary file with integer IDs, one per line
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("123\n456\n789\n101112\n")
temp_file.close()

ARGS = {
    "filename": temp_file.name
}
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 int, 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
make_coord Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ashawkey/dimr/model/bsp.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cxx226/DPF, is pointer only (licence: NONE) · get_code("002a7e71085f0700")
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 cxx226/DPF, 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.

nn_distance Ran
ran on a synthesized input
ashawkey/dimr/model/rfs.py
code served (permissive licence) · get_code("9f96ab7daaf63758")
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 torch

torch.manual_seed(0)

# Create small point clouds
# pc1: (B=2, N=3, C=4) - batch of 2, with 3 points each, 4 coordinates
pc1 = torch.randn(2, 3, 4)

# pc2: (B=2, M=5, C=4) - batch of 2, with 5 points each, 4 coordinates
pc2 = torch.randn(2, 5, 4)

ARGS = {
    'pc1': pc1,
    'pc2': pc2,
    'l1smooth': False,
    'delta': 1.0,
    'l1': False,
}
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 — 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
non_max_suppression Ran
ran on a synthesized input
ashawkey/dimr/model/rfs.py
code served (permissive licence) · get_code("ad0e905aaa1821e5")
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 int, 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

# Create small example data for non_max_suppression
# The function expects:
# - ious: a 2D array of IoU (Intersection over Union) values
# - scores: a 1D array of confidence scores
# - threshold: a float threshold for NMS

# Create a 4x4 IoU matrix (symmetric, with 1s on diagonal)
# This represents IoU between 4 bounding boxes
ious = np.array([
    [1.0, 0.5, 0.2, 0.1],
    [0.5, 1.0, 0.3, 0.2],
    [0.2, 0.3, 1.0, 0.6],
    [0.1, 0.2, 0.6, 1.0]
], dtype=np.float32)

# Create confidence scores for each box
scores = np.array([0.9, 0.8, 0.7, 0.6], dtype=np.float32)

# Set a reasonable NMS threshold
threshold = 0.5

ARGS = {
    'ious': ious,
    'scores': scores,
    'threshold': threshold
}
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 int, 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
read_txt Ran
ran on a synthesized input
ashawkey/dimr/util/visualize.py
code served (permissive licence) · get_code("1152f339832a3ce7")
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 tempfile
import os

# Create a temporary text file with sample content
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.txt")

with open(temp_file, 'w') as f:
    f.write("line one\n")
    f.write("  line two with spaces  \n")
    f.write("line three\n")

ARGS = {
    "file": temp_file
}
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 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
reparametrize Ran
ran on a synthesized input
ashawkey/dimr/model/bsp.py
code served (permissive licence) · get_code("e8fa8332e3980a60")
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)

# Create small tensor arguments for the reparametrize function
mu = torch.randn(2, 4)
log_sigma = torch.randn(2, 4)

ARGS = {
    "mu": mu,
    "log_sigma": log_sigma,
}
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
voc_ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ashawkey/dimr/evaluation/iou/metrics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SupreethN/Hand-CNN, is pointer only (licence: NOASSERTION) · get_code("95c31c78be42f723")
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 SupreethN/Hand-CNN, 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.

voc_ap Ran
ran on a synthesized input
ashawkey/dimr/evaluation/cd/metrics.py
code served (permissive licence) · get_code("8c98f95224124856")
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 float64, ndim 0, 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 small valid arrays for recall and precision
# These should be monotonically increasing-ish arrays with values in [0, 1]
rec = np.array([0.1, 0.3, 0.5, 0.7, 0.9])
prec = np.array([0.95, 0.85, 0.75, 0.65, 0.55])

# use_07_metric can be either True or False
use_07_metric = False

ARGS = {
    "rec": rec,
    "prec": prec,
    "use_07_metric": use_07_metric
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 4 the same month, 5 later) and 9 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
voc_ap 27 other papers
18 dated earlier, 9 later
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1605.06409 (2016-05)
R-FCN: Object Detection via Region-based Fully Convolutional Networks
1609.03605 (2016-09)
Detecting Text in Natural Image with Connectionist Text Proposal Network
and 24 more not named here
intersectionAndUnion 11 other papers
3 dated earlier, 2 the same month, 6 later
2004.01658 (2020-04)
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Huang_PrimitiveNet_Primitive_Instance_Segmentation_With_Local_Primitive_Embedding_Under_Adversarial_ICCV_2021_paper (2021 (year only))
PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric
2108.05293 (2021-08)
Few-Shot Segmentation with Global and Local Contrastive Learning
and 8 more not named here
make_coord 11 other papers
1 dated earlier, 10 later · 5 only as an assembly brick
2112.06174 (2021-12)
Implicit Transformer Network for Screen Content Image Continuous Super-Resolution
2206.04647 (2022-06)
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
2206.08655 (2022-06)
Learning Implicit Feature Alignment Function for Semantic Segmentation
and 8 more not named here
load_ids 5 other papers
1 dated earlier, 1 the same month, 3 later
2004.01658 (2020-04)
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
2203.09065 (2022-03)
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
aaai_25335 (2023 (year only))
Superpoint Transformer for 3D Scene Instance Segmentation
and 2 more not named here
huber_loss 3 other papers
3 later
2401.05011 (2024-01)
Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object Detection
2404.18135 (2024-04)
Dexterous Grasp Transformer
2408.02555 (2024-08)
MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization
is_power2 3 other papers
2 dated earlier, 1 the same month
2004.01658 (2020-04)
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Huang_PrimitiveNet_Primitive_Instance_Segmentation_With_Local_Primitive_Embedding_Under_Adversarial_ICCV_2021_paper (2021 (year only))
PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric
2203.09065 (2022-03)
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
get_instances 2 other papers
1 dated earlier, 1 the same month
2004.01658 (2020-04)
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
2203.09065 (2022-03)
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset

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

Semantic scene reconstruction from point cloud is an essential and challenging task for 3D scene understanding. This task requires not only to recognize each instance in the scene, but also to recover their geometries based on the partial observed point cloud. Existing methods usually attempt to directly predict occupancy values of the complete object based on incomplete point cloud proposals from a detection-based backbone. However, this framework always fails to reconstruct high fidelity mesh due to the obstruction of various detected false positive object proposals and the ambiguity of incomplete point observations for learning occupancy values of complete objects. To circumvent the hurdle, we propose a Disentangled Instance Mesh Reconstruction (DIMR) framework for effective point scene understanding. A segmentation-based backbone is applied to reduce false positive object proposals, which further benefits our exploration on the relationship between recognition and reconstruction. Based on the accurate proposals, we leverage a meshaware latent code space to disentangle the processes of shape completion and mesh generation, relieving the ambiguity caused by the incomplete point observations. Furthermore, with access to the CAD model pool at test time, our model can also be used to improve the reconstruction quality by performing mesh retrieval without extra training. We thoroughly evaluate the reconstructed mesh quality with multiple metrics, and demonstrate the superiority of our method on the challenging Scan-Net dataset. Code is available at https://github.com/ashawkey/dimr.

For agents

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

get_harvested_code_for_paper("2203.16832")
get_code_for_paper("2203.16832")
have("2203.16832")

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

curl https://syntology.ai/api/ran/2203.16832.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.16832.svg)](https://syntology.ai/paper/2203.16832)

Connect an agent — have() is free.