SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.11964 · 2020

LiDAR-based Panoptic Segmentation via Dynamic Shifting Network

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 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/2011.11964.json · badge: /api/ran/2011.11964.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
hongfz16/DS-Net canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
dbscan_cluster Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hongfz16/DS-Net/utils/clustering.py
code served (permissive licence) · get_code("e39fa2b21d0b85df")
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 ndarray, ndim 1, dtype family int, shape (10,) 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 a small point cloud with embedding dimension 4
np.random.seed(0)
shifted_pcd = np.random.randn(10, 4).astype(np.float32)

# Create a valid mask that selects 8 out of 10 points
valid = np.array([True, True, True, True, True, True, True, True, False, False])

ARGS = {
    "shifted_pcd": shifted_pcd,
    "valid": valid,
    "min_samples": 2,
    "eps": 0.5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, sklearn — 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 (10,) — shape (10,) 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
meanshift_cluster Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hongfz16/DS-Net/utils/clustering.py
code served (permissive licence) · get_code("acdac34f73c493a0")
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 ndarray, ndim 1, dtype family int, shape (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

# Set random seed for reproducibility
np.random.seed(0)

# Create shifted_pcd: a 2D array of shape (6, 4) representing point cloud data
# with 6 points in 4-dimensional embedding space
shifted_pcd = np.random.randn(6, 4).astype(np.float32)

# Create valid: a boolean mask indicating which points are valid
# True for indices 0, 1, 2, 4 (4 valid points out of 6)
valid = np.array([True, True, True, False, True, False], dtype=bool)

# bandwidth parameter for MeanShift clustering
bandwidth = 0.5

ARGS = {
    "shifted_pcd": shifted_pcd,
    "valid": valid,
    "bandwidth": bandwidth,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, sklearn — 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 (6,) — shape (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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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
dbscan_cluster 1 other paper
1 later
2203.07186 (2022-03)
LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network
meanshift_cluster 1 other paper
1 later
2203.07186 (2022-03)
LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network

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

With the rapid advances of autonomous driving, it becomes critical to equip its sensing system with more holistic 3D perception. However, existing works focus on parsing either the objects (e.g. cars and pedestrians) or scenes (e.g. trees and buildings) from the LiDAR sensor. In this work, we address the task of LiDAR-based panoptic segmentation, which aims to parse both objects and scenes in a unified manner. As one of the first endeavors towards this new challenging task, we propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm. In particular, DS-Net has three appealing properties: 1) strong backbone design. DS-Net adopts the cylinder convolution that is specifically designed for LiDAR point clouds. The extracted features are shared by the semantic branch and the instance branch which operates in a bottom-up clustering style. 2) Dynamic Shifting for complex point distributions. We observe that commonly-used clustering algorithms like BFS or DBSCAN are incapable of handling complex autonomous driving scenes with non-uniform point cloud distributions and varying instance sizes. Thus, we present an efficient learnable clustering module, dynamic shifting, which adapts kernel functions on-the-fly for different instances. 3) Consensus-driven Fusion. Finally, consensus-driven fusion is used to deal with the disagreement between semantic and instance predictions. To comprehensively evaluate the performance of LiDAR-based panoptic segmentation, we construct and curate benchmarks from two large-scale autonomous driving LiDAR datasets, SemanticKITTI and nuScenes. Extensive experiments demonstrate that our proposed DS-Net achieves superior accuracies over current state-of-the-art methods. Notably, we achieve 1st place on the public leaderboard of SemanticKITTI, outperforming 2nd place by 2.6% in terms of the PQ metric.

For agents

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

get_harvested_code_for_paper("2011.11964")
get_code_for_paper("2011.11964")
have("2011.11964")

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

curl https://syntology.ai/api/ran/2011.11964.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.11964.svg)](https://syntology.ai/paper/2011.11964)

Connect an agent — have() is free.