SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.01264 · ICLR · 2022

Probabilistic Implicit Scene Completion

Dongsu Zhang, Changwoon Choi, Young Kim, Inbum Park

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 1 has no contract verdict; 2 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/2204.01264.json · badge: /api/ran/2204.01264.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
96lives/gca canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
iclr2022submission4/cgca canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
chamfer_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
96lives/gca/baselines/common.py
code served (permissive licence) · get_code("abfc6cc1d6dbd59b")
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; 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 point cloud tensors
# Shape: (batch_size=2, num_points=4, coordinates=3)
points1 = torch.randn(2, 4, 3)
points2 = torch.randn(2, 4, 3)

# Mock function for get_nearest_neighbors_indices_batch since it's called but not defined
def get_nearest_neighbors_indices_batch(points1_np, points2_np):
    """Mock KD-tree nearest neighbor function."""
    batch_size = points1_np.shape[0]
    num_points1 = points1_np.shape[1]
    num_points2 = points2_np.shape[1]
    # Return random indices and distances
    idx = np.random.randint(0, num_points2, size=(batch_size, num_points1))
    distances = np.random.rand(batch_size, num_points1)
    return idx, distances

# Inject the mock function into the module namespace
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'get_nearest_neighbors_indices_batch', get_nearest_neighbors_indices_batch)

ARGS = {
    "points1": points1,
    "points2": points2,
    "use_kdtree": False,
    "give_id": False
}
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 1, dtype family float — no output shape is stated: observe_signature.py could not observe it (fixture:KeyError)
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
chamfer_distance_naive Ran
ran; our contract draft was wrong, not the code
96lives/gca/baselines/common.py
code served (permissive licence) · get_code("8e6b5059f61d84e6")
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
import numpy as np

torch.manual_seed(0)

# The function expects two tensors of point clouds
# Shape: (batch_size, num_points, 3)
# The function uses .size(), .view(), .pow(), .sum(), .min(), .mean()
# So we need torch tensors, not numpy arrays

batch_size = 2
num_points = 4
point_dim = 3

points1 = torch.randn(batch_size, num_points, point_dim)
points2 = torch.randn(batch_size, num_points, point_dim)

ARGS = {
    "points1": points1,
    "points2": points2,
}
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 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
change_feat Ran
ran on a synthesized input
iclr2022submission4/cgca/datasets/transition_dataset.py
code served (permissive licence) · get_code("e0ca66b21c03393b")
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 function. 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)

# Create a small stand-in class for the object that will be passed as args[0]
class MockModel:
    def __init__(self, config):
        self.config = config

# Create a simple function to be decorated
def dummy_function(model):
    return {
        'state_feat': torch.randn(2, 4)
    }

# Apply the decorator
def change_feat(f):
    def wrapper(*args):
        data = f(*args)
        if args[0].config['model'] == 'gca':
            data['state_feat'] = torch.ones(data['state_feat'].shape[0], 1)
        elif args[0].config['model'] == 'cgca_transition_condition':
            data['state_feat'] = torch.zeros(data['state_feat'].shape[0], args[0].config['z_dim'])
        return data
    return wrapper

decorated_function = change_feat(dummy_function)

# Create arguments for calling the decorated function
config_gca = {
    'model': 'gca',
    'z_dim': 8
}

mock_model = MockModel(config_gca)

ARGS = {
    'f': decorated_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_iou Ran
ran, honoured the contract we drafted
96lives/gca/baselines/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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
compute_iou 9 other papers
4 dated earlier, 5 later
2003.04618 (2020-03)
Convolutional Occupancy Networks
2104.01148 (2021-04)
Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
2107.01899 (2021-07)
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
and 6 more not named here
chamfer_distance_naive 6 other papers
2 dated earlier, 4 later
2003.04618 (2020-03)
Convolutional Occupancy Networks
2107.01899 (2021-07)
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
2206.01724 (2022-06)
SNAKE: Shape-aware Neural 3D Keypoint Field
and 3 more not named here
chamfer_distance 3 other papers
1 dated earlier, 2 later
2107.01899 (2021-07)
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
2206.01724 (2022-06)
SNAKE: Shape-aware Neural 3D Keypoint Field
2309.05098 (2023-09)
3D Implicit Transporter for Temporally Consistent Keypoint Discovery

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a probabilistic shape completion method extended to the continuous geometry of large-scale 3D scenes. Real-world scans of 3D scenes suffer from a considerable amount of missing data cluttered with unsegmented objects. The problem of shape completion is inherently ill-posed, and high-quality result requires scalable solutions that consider multiple possible outcomes. We employ the Generative Cellular Automata that learns the multi-modal distribution and transform the formulation to process large-scale continuous geometry. The local continuous shape is incrementally generated as a sparse voxel embedding, which contains the latent code for each occupied cell. We formally derive that our training objective for the sparse voxel embedding maximizes the variational lower bound of the complete shape distribution and therefore our progressive generation constitutes a valid generative model. Experiments show that our model successfully generates diverse plausible scenes faithful to the input, especially when the input suffers from a significant amount of missing data. We also demonstrate that our approach outperforms deterministic models even in less ambiguous cases with a small amount of missing data, which infers that probabilistic formulation is crucial for high-quality geometry completion on input scans exhibiting any levels of completeness.

For agents

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

get_harvested_code_for_paper("2204.01264")
get_code_for_paper("2204.01264")
have("2204.01264")

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

curl https://syntology.ai/api/ran/2204.01264.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.01264.svg)](https://syntology.ai/paper/2204.01264)

Connect an agent — have() is free.