SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2512.07599 · NeurIPS · 2025

Online Segment Any 3D Thing as Instance Tracking

Ke Wang, Jin Gao, Weiming Hu, Zijian Cai, Zhipeng Zhang, Yiwei Zhang, Hanshi Wang

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 0 have no contract verdict; 3 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/2512.07599.json · badge: /api/ran/2512.07599.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
AutoLab-SAI-SJTU/AutoSeg3D canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
adjust_intrinsic Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AutoLab-SAI-SJTU/AutoSeg3D/oneformer3d/formatting.py
code served (permissive licence) · get_code("81a52f12291c03c6")
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 (3, 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
import math
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - intrinsic: a 2D array/tensor that gets indexed with [0, 0], [1, 1], [0, 2], [1, 2]
#   and elements are multiplied. This is a camera intrinsic matrix (typically 3x3).
# - intrinsic_image_dim: tuple/list with 2 elements (height, width of original image)
# - image_dim: tuple/list with 2 elements (height, width of target image)

# Create a sample camera intrinsic matrix (3x3)
intrinsic = torch.tensor([
    [500.0, 0.0, 320.0],
    [0.0, 500.0, 240.0],
    [0.0, 0.0, 1.0]
], dtype=torch.float32)

# Original image dimensions (height, width)
intrinsic_image_dim = (480, 640)

# Target image dimensions (height, width) - different from original
image_dim = (240, 320)

ARGS = {
    "intrinsic": intrinsic,
    "intrinsic_image_dim": intrinsic_image_dim,
    "image_dim": image_dim,
}
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 2, dtype family float, shape (3, 3) — shape (3, 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
build_pairwise_mask Ran
ran; our contract draft was wrong, not the code
AutoLab-SAI-SJTU/AutoSeg3D/oneformer3d/dq_utils.py
code served (permissive licence) · get_code("dfcc5c5f08448dec")
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)

# Define the arguments for build_pairwise_mask
ARGS = {
    "merged_groups": [
        [0, 1, 3],      # Group 1: samples 0, 1, 3 belong to same object
        [2, 4],         # Group 2: samples 2, 4 belong to same object
        [5]             # Group 3: sample 5 alone
    ],
    "compact": False,
    "device": "cpu",
    "max_value": -1,
    "scale": False,
    "low": 0.05,
    "high": 0.95
}
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
cluster_with_threshold Ran
ran; our contract draft was wrong, not the code
AutoLab-SAI-SJTU/AutoSeg3D/oneformer3d/dq_utils.py
code served (permissive licence) · get_code("0d03cb242852337e")
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. 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 a similarity matrix [N, N] with values between 0 and 1
# Using N=5 for a small but non-trivial test case
sim_mat = torch.tensor([
    [1.0, 0.8, 0.3, 0.2, 0.1],
    [0.8, 1.0, 0.4, 0.15, 0.05],
    [0.3, 0.4, 1.0, 0.9, 0.2],
    [0.2, 0.15, 0.9, 1.0, 0.6],
    [0.1, 0.05, 0.2, 0.6, 1.0]
], dtype=torch.float32)

ARGS = {
    "sim_mat": sim_mat,
    "thresh": 0.75
}
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 list — a list 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
make_intrinsic Ran
ran, honoured the contract we drafted
AutoLab-SAI-SJTU/AutoSeg3D/oneformer3d/formatting.py
code served (permissive licence) · get_code("f47c8e54943ce833")
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 (4, 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 valid arguments for make_intrinsic
# The function takes 4 scalar parameters: fx, fy, mx, my (focal lengths and principal point)

ARGS = {
    "fx": 500.0,
    "fy": 500.0,
    "mx": 320.0,
    "my": 240.0,
}
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 ndarray, ndim 2, dtype family float, shape (4, 4) — shape (4, 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 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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
adjust_intrinsic 4 other papers
4 dated earlier
2205.13490 (2022-05)
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
2311.17707 (2023-11)
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation
2312.10671 (2023-12)
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance
and 1 more not named here
make_intrinsic 4 other papers
4 dated earlier
2205.13490 (2022-05)
SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation
2311.17707 (2023-11)
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation
2312.10671 (2023-12)
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance
and 1 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

Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments. Recent advancements employ predefined object queries to aggregate semantic information from Vision Foundation Models (VFMs) outputs that are lifted into 3D point clouds, facilitating spatial information propagation through inter-query interactions. Nevertheless, perception, whether human or robotic, is an inherently dynamic process, rendering temporal understanding a critical yet overlooked dimension within these prevailing query-based pipelines. This deficiency in temporal reasoning can exacerbate issues such as the over-segmentation commonly produced by VFMs, necessitating more handcrafted post-processing. Therefore, to further unlock the temporal environmental perception capabilities of embodied agents, our work reconceptualizes online 3D segmentation as an instance tracking problem (AutoSeg3D). Our core strategy involves utilizing object queries for temporal information propagation, where long-term instance association promotes the coherence of features and object identities, while short-term instance update enriches instant observations. Given that viewpoint variations in embodied robotics often lead to partial object visibility across frames, this mechanism aids the model in developing a holistic object understanding beyond incomplete instantaneous views. Furthermore, we introduce spatial consistency learning to mitigate the fragmentation problem inherent in VFMs, yielding more comprehensive instance information for enhancing the efficacy of both long-term and short-term temporal learning. The temporal information exchange and consistency learning facilitated by these sparse object queries not only enhance spatial comprehension but also circumvent the computational burden associated with dense temporal point cloud interactions. Our method establishes a new state-of-the-art, surpassing ESAM by 2.8 AP on Scan-Net200 and delivering consistent gains on ScanNet, SceneNN, and 3RScan datasets, corroborating that identity-aware temporal reasoning is a crucial, previously underemphasized component for robust 3D segmentation in real-time embodied intelligence. Code is at https://github.com/AutoLab-SAI-SJTU/AutoSeg3D.

For agents

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

get_harvested_code_for_paper("2512.07599")
get_code_for_paper("2512.07599")
have("2512.07599")

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

curl https://syntology.ai/api/ran/2512.07599.json

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

[![Syntology run record](https://syntology.ai/api/ran/2512.07599.svg)](https://syntology.ai/paper/2512.07599)

Connect an agent — have() is free.