SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.04680 · 2021

SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 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/2112.04680.json · badge: /api/ran/2112.04680.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
zhyever/simipu canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_final_epoch Ran
ran, honoured the contract we drafted
zhyever/simipu/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("5a5bcd643adcbecc")
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 int, ndim 0, dtype family int, shape () 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 numpy as np

def get_final_epoch(config):
    SCHEDULES_LUT = {'_1x_': 12, '_2x_': 24, '_20e_': 20, '_3x_': 36, '_4x_': 48, '_24e_': 24, '_6x_': 73, '_50e_': 50, '_80e_': 80, '_200e_': 200, '_250e_': 250}
    if config.find('grid_rcnn') != -1 and config.find('2x') != -1:
        return 25
    for schedule_name, epoch_num in SCHEDULES_LUT.items():
        if config.find(schedule_name) != -1:
            return epoch_num

ARGS = {
    'config': 'model_grid_rcnn_2x_backbone'
}
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 int, ndim 0, dtype family int, shape () — shape () 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_model_dataset Ran
ran; our contract draft was wrong, not the code
zhyever/simipu/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("266b220fd05d5e7f")
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 str. 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

# The function takes a log_json_path parameter and searches for dataset keywords
# It doesn't actually use the path for I/O, just string matching
# So we need to provide a string path that contains one of the dataset keys

log_json_path = "/logs/coco_results_2024.json"

ARGS = {
    "log_json_path": log_json_path
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
process_checkpoint Ran
ran; our contract draft was wrong, not the code
zhyever/simipu/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("e76a491553cf9fcf")
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 str. 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 tempfile
import os

torch.manual_seed(0)

# Create a temporary directory for checkpoint files
temp_dir = tempfile.mkdtemp()

# Create a minimal checkpoint dict with a model state and optimizer
checkpoint = {
    'model': {
        'layer1.weight': torch.randn(4, 3),
        'layer1.bias': torch.randn(4),
    },
    'optimizer': {
        'state': {},
        'param_groups': [],
    },
    'epoch': 1,
}

# Save the checkpoint to a temporary file
in_file = os.path.join(temp_dir, 'checkpoint.pth')
torch.save(checkpoint, in_file)

# Define output file path
out_file = os.path.join(temp_dir, 'checkpoint_processed.pth')

ARGS = {
    'in_file': in_file,
    'out_file': out_file,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 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
process_checkpoint 45 other papers
15 dated earlier, 29 later, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 42 more not named here
get_final_epoch 35 other papers
9 dated earlier, 25 later, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 32 more not named here
get_model_dataset 26 other papers
2 dated earlier, 23 later, 1 undated
2104.06114 (2021-04)
Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
2104.10956 (2021-04)
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
2203.07697 (2022-03)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
and 23 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

Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional space, such pre-trained models fail to perceive spatial information and serve as sub-optimal solutions for 3D-related tasks. To bridge this gap, we aim to learn a spatial-aware visual representation that can describe the three-dimensional space and is more suitable and effective for these tasks. To leverage point clouds, which are much more superior in providing spatial information compared to images, we propose a simple yet effective 2D Image and 3D Point cloud Unsupervised pre-training strategy, called SimIPU. Specifically, we develop a multi-modal contrastive learning framework that consists of an intra-modal spatial perception module to learn a spatial-aware representation from point clouds and an inter-modal feature interaction module to transfer the capability of perceiving spatial information from the point cloud encoder to the image encoder, respectively. Positive pairs for contrastive losses are established by the matching algorithm and the projection matrix. The whole framework is trained in an unsupervised end-to-end fashion. To the best of our knowledge, this is the first study to explore contrastive learning pre-training strategies for outdoor multi-modal datasets, containing paired camera images and LIDAR point clouds. Codes and models are available at https://github.com/zhyever/SimIPU.

For agents

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

get_harvested_code_for_paper("2112.04680")
get_code_for_paper("2112.04680")
have("2112.04680")

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

curl https://syntology.ai/api/ran/2112.04680.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.04680.svg)](https://syntology.ai/paper/2112.04680)

Connect an agent — have() is free.