SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.02493 · 2021

Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting

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/2107.02493.json · badge: /api/ran/2107.02493.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
cxmomo/Neighbor-Vote canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
checkpoint_state Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cxmomo/Neighbor-Vote/tools/train_utils/train_utils.py
code served (permissive licence) · get_code("fd2419c962c52a58")
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
import torch.optim as optim

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate model
model = SimpleModel()

# Create optimizer
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Epoch and iteration counters
epoch = 5
it = 100

ARGS = {
    'model': model,
    'optimizer': optimizer,
    'epoch': epoch,
    'it': it
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
pcdet, 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
model_state_to_cpu Ran
ran; our contract draft was wrong, not the code
cxmomo/Neighbor-Vote/tools/train_utils/train_utils.py
code served (permissive licence) · get_code("51ce1f7d0c5be36c")
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)

# The function expects model_state to be a dict-like object where:
# - It can be instantiated with type(model_state)()
# - It has .items() method
# - Values have .cpu() method (i.e., tensors)

# Create a model state dict with some tensors on CPU
model_state = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'layer2.weight': torch.randn(5, 4),
    'layer2.bias': torch.randn(5),
}

ARGS = {
    'model_state': model_state
}
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
train_one_epoch Ran
ran, honoured the contract we drafted
cxmomo/Neighbor-Vote/tools/train_utils/train_utils.py
code served (permissive licence) · get_code("0a2dfbac7583d7bc")
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 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 torch.nn as nn
from torch.optim import Adam
from torch.optim.lr_scheduler import StepLR
import tqdm

torch.manual_seed(0)

# Define a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Define a minimal config object
class OptimConfig:
    def __init__(self):
        self.GRAD_NORM_CLIP = 1.0

# Define a minimal tensorboard logger
class TBLog:
    def add_scalar(self, tag, value, step):
        pass

# Define a minimal model_func that returns loss, tb_dict, disp_dict
def model_func(model, batch):
    x, y = batch
    output = model(x)
    loss = ((output - y) ** 2).mean()
    tb_dict = {'aux_loss': torch.tensor(0.1)}
    disp_dict = {'acc': 0.95}
    return loss, tb_dict, disp_dict

# Create model and optimizer
model = SimpleModel()
optimizer = Adam(model.parameters(), lr=0.001)

# Create a simple train loader with 3 batches
train_loader = [
    (torch.randn(2, 4), torch.randn(2, 3)),
    (torch.randn(2, 4), torch.randn(2, 3)),
    (torch.randn(2, 4), torch.randn(2, 3)),
]

# Create lr_scheduler
lr_scheduler = StepLR(optimizer, step_size=1, gamma=0.9)

# Create tqdm progress bar for outer loop
tbar = tqdm.tqdm(total=1, desc='epoch', leave=False)

# Create tensorboard logger
tb_log = TBLog()

# Define ARGS dictionary
ARGS = {
    'model': model,
    'optimizer': optimizer,
    'train_loader': train_loader,
    'model_func': model_func,
    'lr_scheduler': lr_scheduler,
    'accumulated_iter': 0,
    'optim_cfg': OptimConfig(),
    'rank': 0,
    'tbar': tbar,
    'total_it_each_epoch': 3,
    'dataloader_iter': iter(train_loader),
    'tb_log': tb_log,
    'leave_pbar': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, tqdm — 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

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, 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 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
model_state_to_cpu 1 other paper
1 later
2312.08022 (2023-12)
Mono3DVG: 3D Visual Grounding in Monocular Images

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

As cameras are increasingly deployed in new application domains such as autonomous driving, performing 3D object detection on monocular images becomes an important task for visual scene understanding. Recent advances on monocular 3D object detection mainly rely on the ``pseudo-LiDAR'' generation, which performs monocular depth estimation and lifts the 2D pixels to pseudo 3D points. However, depth estimation from monocular images, due to its poor accuracy, leads to inevitable position shift of pseudo-LiDAR points within the object. Therefore, the predicted bounding boxes may suffer from inaccurate location and deformed shape. In this paper, we present a novel neighbor-voting method that incorporates neighbor predictions to ameliorate object detection from severely deformed pseudo-LiDAR point clouds. Specifically, each feature point around the object forms their own predictions, and then the ``consensus'' is achieved through voting. In this way, we can effectively combine the neighbors' predictions with local prediction and achieve more accurate 3D detection. To further enlarge the difference between the foreground region of interest (ROI) pseudo-LiDAR points and the background points, we also encode the ROI prediction scores of 2D foreground pixels into the corresponding pseudo-LiDAR points. We conduct extensive experiments on the KITTI benchmark to validate the merits of our proposed method. Our results on the bird's eye view detection outperform the state-of-the-art performance by a large margin, especially for the ``hard'' level detection.

For agents

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

get_harvested_code_for_paper("2107.02493")
get_code_for_paper("2107.02493")
have("2107.02493")

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

curl https://syntology.ai/api/ran/2107.02493.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.02493.svg)](https://syntology.ai/paper/2107.02493)

Connect an agent — have() is free.