SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.09440 · ECCV · 2022

TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes

Xiaoguang Han, Haolin Liu, Pei Chen, Mutian Xu

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 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/2203.09440.json · badge: /api/ran/2203.09440.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
GAP-LAB-CUHK-SZ/TO-Scene canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
flip_axis_to_camera Ran
ran, honoured the contract we drafted
GAP-LAB-CUHK-SZ/TO-Scene/obj_det/models/ap_helper.py
pointer only (licence: MIT); the stored copy get_code serves, from tingxueronghua/dpke, is pointer only (licence: NONE) · get_code("eddd23cbbb297813")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tingxueronghua/dpke, 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.

flip_axis_to_depth Ran
ran, honoured the contract we drafted
GAP-LAB-CUHK-SZ/TO-Scene/obj_det/models/ap_helper.py
code served (permissive licence) · get_code("d638b0201b9a9ece")
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 2, dtype family float, 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 numpy as np

# The function takes a point cloud (pc) which is a numpy array
# It performs axis flipping and negation operations on it
# The array has shape (..., 3) where the last dimension contains [x, y, z] coordinates

# Create a small point cloud array with shape (2, 3)
# This represents 2 points in 3D space
pc = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0]
], dtype=np.float32)

ARGS = {
    "pc": pc
}
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 2, dtype family float, 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
get_color Ran
ran, violated the contract we drafted
GAP-LAB-CUHK-SZ/TO-Scene/sem_seg/vis_tocrowd.py
code served (permissive licence) · get_code("d01e418562a2f61b")
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) and returned tuple, ndim 1, 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

ARGS = {
    "i": 16711680
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
rotate_aligned_boxes Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GAP-LAB-CUHK-SZ/TO-Scene/obj_det/dataset/TOS_scene_dataset.py
code served (permissive licence) · get_code("7457a44fbe4c2d1d")
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 2, dtype family float, shape (2, 6) 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

# Construct input_boxes: shape (batch_size, 6)
# First 3 columns are centers (x, y, z)
# Next 3 columns are lengths (dx, dy, dz)
input_boxes = np.array([
    [1.0, 2.0, 3.0, 4.0, 5.0, 6.0],
    [0.5, 1.5, 2.5, 3.0, 4.0, 5.0]
], dtype=np.float32)

# Construct rot_mat: 3x3 rotation matrix
# Using a simple rotation matrix (45 degrees around z-axis)
angle = np.pi / 4
rot_mat = np.array([
    [np.cos(angle), -np.sin(angle), 0.0],
    [np.sin(angle), np.cos(angle), 0.0],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

ARGS = {
    "input_boxes": input_boxes,
    "rot_mat": rot_mat
}
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 2, dtype family float, shape (2, 6) — shape (2, 6) 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
softmax Ran
ran, honoured the contract we drafted
GAP-LAB-CUHK-SZ/TO-Scene/obj_det/models/ap_helper.py
code served (permissive licence) · get_code("1a034a72c15f9903")
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 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 numpy as np

# Construct a small numpy array for the softmax function
# The function operates on the last axis, so we'll create a 2D array
# to demonstrate typical usage
x = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 1.0, 4.0, 3.0]
], dtype=np.float32)

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 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
decode_scores Not yet run
unverified (harvested, no recorded run)
GAP-LAB-CUHK-SZ/TO-Scene/obj_det/models/proposal_module.py
code served (permissive licence) · get_code("74b9f07a52401d24")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 3 the same month, 5 later) and 0 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
flip_axis_to_camera 10 other papers
3 dated earlier, 1 the same month, 6 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1912.11803 (2019-12)
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
2004.05679 (2020-04)
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
and 7 more not named here
softmax 9 other papers
3 dated earlier, 1 the same month, 5 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1912.11803 (2019-12)
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
2004.05679 (2020-04)
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
and 6 more not named here
flip_axis_to_depth 7 other papers
2 dated earlier, 1 the same month, 4 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1912.11803 (2019-12)
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
2203.05203 (2022-03)
MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes
and 4 more not named here
decode_scores 4 other papers
3 dated earlier, 1 later
1904.09664 (2019-04)
Deep Hough Voting for 3D Object Detection in Point Clouds
1912.11803 (2019-12)
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
2004.05679 (2020-04)
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
and 1 more not named here
rotate_aligned_boxes 2 other papers
2 later
2309.11133 (2023-09)
Shape Anchor Guided Holistic Indoor Scene Understanding
2407.06084 (2024-07)
3D Vision and Language Pretraining with Large-Scale Synthetic Data
get_color 1 other paper
1 dated earlier
1702.01105 (2017-02)
Joint 2D-3D-Semantic Data for Indoor Scene Understanding

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

TO_ScanNet o b j in w h o le ro o m Transfer obj CADs onto real tables, by crowdsourcing Web UI Object CADs from ModelNet or ShapeNet TO_Vanilla Real Tables from ScanNet Source Datasets TO-Real Test up load sim to real autolabel TO_Crowd in cr ea se ob j TO-Scene Build * M. Xu and P. Chen contribute equally. † Corresponding author. Xu et al. scanned test set TO-Real to verify the practical value of TO-Scene. Experiments show that the algorithms trained on TO-Scene indeed work on the realistic test data, and our proposed tabletop-aware learning strategy greatly improves the state-of-the-art results on both 3D semantic segmentation and object detection tasks. Dataset and code are available at https://github.com/GAP-LAB-CUHK-SZ/TO-Scene.

For agents

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

get_harvested_code_for_paper("2203.09440")
get_code_for_paper("2203.09440")
have("2203.09440")

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

curl https://syntology.ai/api/ran/2203.09440.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.09440.svg)](https://syntology.ai/paper/2203.09440)

Connect an agent — have() is free.