SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.10084 · ECCV · 2024

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

Bin Yang, Yuexin Ma, Jiajin Tang, Sibei Yang, Cheng Shi, Yulin Zhang

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 3 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/2407.10084.json · badge: /api/ran/2407.10084.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
chengshiest/part2object canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
batch_dice_loss Ran
ran; our contract draft was wrong, not the code
chengshiest/part2object/models/matcher.py
code served (permissive licence) · get_code("bc2cb481a75c370d")
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, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for inputs and targets
# inputs: arbitrary shape float tensor (predictions)
# targets: same shape as inputs, binary classification labels (0 or 1)
# Using shape (2, 4) - batch size 2, 4 features
inputs = torch.randn(2, 4, dtype=torch.float32)
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)

ARGS = {
    'inputs': inputs,
    'targets': targets,
}
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, 2) — shape (2, 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
dice_loss Ran
ran; our contract draft was wrong, not the code
chengshiest/part2object/models/criterion.py
code served (permissive licence) · get_code("b270cbbfbd5c7d44")
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)

# Create small tensors for inputs and targets
# inputs: arbitrary shape float tensor (predictions)
# targets: same shape as inputs, binary labels (0 or 1)
inputs = torch.randn(2, 4, requires_grad=True)  # batch_size=2, features=4
targets = torch.randint(0, 2, (2, 4)).float()  # same shape, binary values

# num_masks: float representing number of masks
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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
get_iou Ran
ran; our contract draft was wrong, not the code
chengshiest/part2object/models/criterion.py
code served (permissive licence) · get_code("5ea6027b55d9b643")
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)

# The function expects two tensors with the same shape
# It applies sigmoid, binarization, and computes IoU
# The tensors should have at least one dimension for the sum(-1) operation

ARGS = {
    "inputs": torch.randn(2, 4),
    "targets": torch.randn(2, 4),
}
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
make_pred_info Ran
ran; our contract draft was wrong, not the code
chengshiest/part2object/benchmark/evaluate_semantic_instance.py
code served (permissive licence) · get_code("da426b749d2b3e6b")
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 torch
import numpy as np
from uuid import uuid4

torch.manual_seed(0)

# Construct a valid pred dict for make_pred_info
# The function expects:
# - pred['pred_classes']: tensor of class labels, shape [num_objects]
# - pred['pred_scores']: tensor of confidence scores, shape [num_objects]
# - pred['pred_masks']: tensor of masks, shape [height, num_objects]

num_objects = 3
height = 4

pred = {
    'pred_classes': torch.tensor([0, 1, 2]),  # 3 class labels
    'pred_scores': torch.tensor([0.9, 0.8, 0.7]),  # 3 confidence scores
    'pred_masks': torch.rand(height, num_objects)  # shape [4, 3]
}

ARGS = {
    'pred': pred
}
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 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
nested_tensor_from_tensor_list Ran
ran; our contract draft was wrong, not the code
chengshiest/part2object/models/misc.py
code served (permissive licence) · get_code("58cc9ff3bf75e753")
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 NestedTensor. 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.functional as F
from typing import List

torch.manual_seed(0)

# Create a list of 3D tensors with varying shapes
# Each tensor has shape (C, H, W) where C is channels, H is height, W is width
tensor1 = torch.randn(3, 4, 5)  # 3 channels, 4 height, 5 width
tensor2 = torch.randn(3, 6, 7)  # 3 channels, 6 height, 7 width
tensor3 = torch.randn(3, 5, 8)  # 3 channels, 5 height, 8 width

tensor_list = [tensor1, tensor2, tensor3]

ARGS = {
    "tensor_list": tensor_list
}
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 NestedTensor — a NestedTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a NestedTensor 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
shift_scale_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chengshiest/part2object/models/position_embedding.py
code served (permissive licence) · get_code("818099bdffc93897")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create pred_xyz: B x N x 3
# B=2 (batch), N=4 (num points), 3 (xyz coordinates)
pred_xyz = torch.randn(2, 4, 3)

# Create src_range: [[B x 3], [B x 3]] - min and max XYZ coords
# B=2, 3 coordinates
src_min = torch.tensor([[0.0, 0.0, 0.0], [1.0, 1.0, 1.0]])
src_max = torch.tensor([[10.0, 10.0, 10.0], [11.0, 11.0, 11.0]])
src_range = [src_min, src_max]

# Create dst_range: [[B x 3], [B x 3]] - min and max XYZ coords
# B=2, 3 coordinates
dst_min = torch.tensor([[-1.0, -1.0, -1.0], [0.0, 0.0, 0.0]])
dst_max = torch.tensor([[1.0, 1.0, 1.0], [2.0, 2.0, 2.0]])
dst_range = [dst_min, dst_max]

ARGS = {
    "pred_xyz": pred_xyz,
    "src_range": src_range,
    "dst_range": dst_range,
}
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sigmoid_ce_loss Ran
ran; our contract draft was wrong, not the code
chengshiest/part2object/models/criterion.py
code served (permissive licence) · get_code("c0938fc9bc7ebddd")
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 torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
num_elements = 4

# inputs: logits tensor, shape (batch_size, num_elements)
inputs = torch.randn(batch_size, num_elements)

# targets: binary labels tensor, same shape as inputs
targets = torch.randint(0, 2, (batch_size, num_elements)).float()

# num_masks: a float value representing number of masks
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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
batch_sigmoid_ce_loss Not yet run
unverified (harvested, no recorded run)
chengshiest/part2object/models/matcher.py
code served (permissive licence) · get_code("1edd24985036b0bf")
How it ran

no invocation recorded.

compute_averages Not yet run
unverified (harvested, no recorded run)
chengshiest/part2object/benchmark/evaluate_semantic_instance.py
code served (permissive licence) · get_code("0ff7346cfa2f35ee")
How it ran

no invocation recorded.

evaluate_matches Not yet run
unverified (harvested, no recorded run)
chengshiest/part2object/benchmark/evaluate_semantic_instance.py
code served (permissive licence) · get_code("9ae40dc3d72a968c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 3 the same month, 4 later) and 5 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
nested_tensor_from_tensor_list 55 other papers
44 dated earlier, 2 the same month, 7 later, 2 same year, order not determinable · 17 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2101.01909 (2021-01)
Line Segment Detection Using Transformers without Edges
and 52 more not named here
batch_dice_loss 44 other papers
34 dated earlier, 1 the same month, 8 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
batch_sigmoid_ce_loss 44 other papers
34 dated earlier, 1 the same month, 8 later, 1 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
shift_scale_points 11 other papers
8 dated earlier, 2 later, 1 same year, order not determinable · 1 only as an assembly brick
2109.08141 (2021-09)
An End-to-End Transformer Model for 3D Object Detection
2210.03105 (2022-10)
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
2301.02508 (2023-01)
End-to-End 3D Dense Captioning with Vote2Cap-DETR
and 8 more not named here
make_pred_info 1 other paper
1 dated earlier
2210.03105 (2022-10)
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

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

Unsupervised 3D instance segmentation aims to segment objects from a 3D point cloud without any annotations. Existing methods face the challenge of either too loose or too tight clustering, leading to under-segmentation or over-segmentation. To address this issue, we propose Part2Object, hierarchical clustering with object guidance. Part2Object employs multi-layer clustering from points to object parts and objects, allowing objects to manifest at any layer. Additionally, it extracts and utilizes 3D objectness priors from temporally consecutive 2D RGB frames to guide the clustering process. Moreover, we propose Hi-Mask3D to support hierarchical 3D object part and instance segmentation. By training Hi-Mask3D on the objects and object parts extracted from Part2Object, we achieve consistent and superior performance compared to state-of-the-art models in various settings, including unsupervised instance segmentation, data-efficient fine-tuning, and cross-dataset generalization. Code is release at https://github.com/ChengShiest/ Part2Object.

For agents

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

get_harvested_code_for_paper("2407.10084")
get_code_for_paper("2407.10084")
have("2407.10084")

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

curl https://syntology.ai/api/ran/2407.10084.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.10084.svg)](https://syntology.ai/paper/2407.10084)

Connect an agent — have() is free.