SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.13971 · 2020

Accurate, Low-Latency Visual Perception for Autonomous Racing:Challenges, Mechanisms, and Practical Solutions

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 1 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/2007.13971.json · badge: /api/ran/2007.13971.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
cv-core/MIT-Driverless-CV-TrainingInfra canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
eval_model Ran
ran on a synthesized input
cv-core/MIT-Driverless-CV-TrainingInfra/RektNet/keypoint_tutorial_util.py
code served (permissive licence) · get_code("651a7b6fa2ae8d29")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim 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)

# Define a simple model that outputs two tensors (location and geometric predictions)
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2_loc = nn.Linear(8, 6)
        self.fc2_geo = nn.Linear(8, 6)
    
    def forward(self, x):
        h = torch.relu(self.fc1(x))
        loc_output = self.fc2_loc(h)
        geo_output = self.fc2_geo(h)
        return (loc_output, geo_output)

# Define a simple loss function that takes the model outputs and targets
def simple_loss_function(loc_output, geo_output, y_hm_batch, y_point_batch):
    loc_loss = torch.nn.functional.mse_loss(loc_output, y_hm_batch)
    geo_loss = torch.nn.functional.mse_loss(geo_output, y_point_batch)
    total_loss = loc_loss + geo_loss
    return (loc_loss, geo_loss, total_loss)

# Create a simple dataloader
model = SimpleModel()

# Create batch data: (x, y_hm, y_point, image_name, unused_fifth_element)
batch_x = torch.randn(2, 4)
batch_y_hm = torch.randn(2, 6)
batch_y_point = torch.randn(2, 6)
image_name = "test_image.jpg"
unused_element = None

dataloader = [
    (batch_x, batch_y_hm, batch_y_point, image_name, unused_element),
    (batch_x, batch_y_hm, batch_y_point, image_name, unused_element),
]

ARGS = {
    'model': model,
    'dataloader': dataloader,
    'loss_function': simple_loss_function,
    'input_size': 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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
prep_image Ran
ran on a synthesized input
cv-core/MIT-Driverless-CV-TrainingInfra/RektNet/utils.py
code served (permissive licence) · get_code("ee94dfaba872016e")
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 3, dtype family int, shape (240, 320, 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 cv2
import numpy as np

torch_manual_seed = 0

# Create a small test image using numpy
# Image shape should be (height, width, channels)
image = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)

# Target image size as (width, height) tuple for cv2.resize
target_image_size = (320, 240)

ARGS = {
    "image": image,
    "target_image_size": target_image_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (240, 320, 3) — shape (240, 320, 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
prep_label Ran
ran on a synthesized input
cv-core/MIT-Driverless-CV-TrainingInfra/RektNet/utils.py
code served (permissive licence) · get_code("1456e0dde12e9929")
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 3, dtype family float, shape (2, 32, 32) 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
import cv2

# Create small test data
label = np.array([
    [10.5, 20.3],
    [15.2, 25.8]
])

target_image_size = (32, 32)
orig_image_size = (64, 64)
image_path = "/fake/path/image.jpg"

ARGS = {
    "label": label,
    "target_image_size": target_image_size,
    "orig_image_size": orig_image_size,
    "image_path": image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 32, 32) — shape (2, 32, 32) 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
vis_tensor_and_save Not yet run
unverified (harvested, no recorded run)
cv-core/MIT-Driverless-CV-TrainingInfra/RektNet/utils.py
code served (permissive licence) · get_code("6bded45c885ac8b3")
How it ran

no invocation recorded.

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Autonomous racing provides the opportunity to test safety-critical perception pipelines at their limit. This paper describes the practical challenges and solutions to applying state-of-the-art computer vision algorithms to build a low-latency, high-accuracy perception system for DUT18 Driverless (DUT18D), a 4WD electric race car with podium finishes at all Formula Driverless competitions for which it raced. The key components of DUT18D include YOLOv3-based object detection, pose estimation, and time synchronization on its dual stereovision/monovision camera setup. We highlight modifications required to adapt perception CNNs to racing domains, improvements to loss functions used for pose estimation, and methodologies for sub-microsecond camera synchronization among other improvements. We perform a thorough experimental evaluation of the system, demonstrating its accuracy and low-latency in real-world racing scenarios.

For agents

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

get_harvested_code_for_paper("2007.13971")
get_code_for_paper("2007.13971")
have("2007.13971")

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

curl https://syntology.ai/api/ran/2007.13971.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.13971.svg)](https://syntology.ai/paper/2007.13971)

Connect an agent — have() is free.