SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.06906 · 2023

Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 failure 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/2304.06906.json · badge: /api/ran/2304.06906.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
microsoft/swin3d canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
load_state_with_same_shape Ran
ran; our contract draft was wrong, not the code
microsoft/swin3d/Swin3D/models/Swin3D.py
code served (permissive licence) · get_code("fda41c833d92c713")
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 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple model with the structure expected by the function
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.stem_layer = nn.Linear(4, 8)
        self.conv1 = nn.Conv2d(3, 16, 3)
        self.classifier = nn.Linear(16, 10)
        self.upsamples = nn.Upsample(scale_factor=2)
        self.fc = nn.Linear(8, 5)
    
    def forward(self, x):
        return x

# Instantiate the model
model = SimpleModel()

# Create weights dict with some matching and some non-matching shapes
weights = {
    'stem_layer.weight': torch.randn(8, 4),
    'stem_layer.bias': torch.randn(8),
    'conv1.weight': torch.randn(16, 3, 3, 3),
    'conv1.bias': torch.randn(16),
    'classifier.weight': torch.randn(10, 16),
    'classifier.bias': torch.randn(10),
    'upsamples.weight': torch.randn(5, 5),
    'fc.weight': torch.randn(5, 8),
    'fc.bias': torch.randn(5),
    'nonexistent_layer.weight': torch.randn(7, 7),
    'conv1.weight_wrong_shape': torch.randn(32, 3, 3, 3),  # Wrong shape
}

ARGS = {
    'model': model,
    'weights': weights,
    'skip_first_conv': False,
    'verbose': True,
}
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 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
load_state_with_same_shape 1 other paper
1 later
2402.14215 (2024-02)
Swin3D++: Effective Multi-Source Pretraining for 3D 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

The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\SST}, for 3D indoor scene understanding. We design a 3D Swin transformer as our backbone network, which enables efficient self-attention on sparse voxels with linear memory complexity, making the backbone scalable to large models and datasets. We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance. We pretrained a large {\SST} model on a synthetic Structured3D dataset, which is an order of magnitude larger than the ScanNet dataset. Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets, but also outperforms state-of-the-art methods on downstream tasks with +2.3 mIoU and +2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation, +1.8 mIoU on ScanNet segmentation (val), +1.9 mAP@0.5 on ScanNet detection, and +8.1 mAP@0.5 on S3DIS detection. A series of extensive ablation studies further validate the scalability, generality, and superior performance enabled by our approach. The code and models are available at https://github.com/microsoft/Swin3D .

For agents

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

get_harvested_code_for_paper("2304.06906")
get_code_for_paper("2304.06906")
have("2304.06906")

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

curl https://syntology.ai/api/ran/2304.06906.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.06906.svg)](https://syntology.ai/paper/2304.06906)

Connect an agent — have() is free.