SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.13164 · CVPR · 2021

M3DSSD: Monocular 3D Single Stage Object Detector

Ling Shao, Yong Ding, Hang Dai, Shujie Luo

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 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/2103.13164.json · badge: /api/ran/2103.13164.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
mumianyuxin/M3DSSD marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
DCNv2 Ran
ran on a synthesized input · constructed an object; no result was computed
mumianyuxin/M3DSSD/model/module/feturealign_mgpu.py
code served (permissive licence) · get_code("763c8ab10252d5bd")
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 an instance of its own class, DCNv2: the run constructed the object and did not call it, so no result was computed. 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 math

torch.manual_seed(0)

# Set up dimensions
batch_size = 2
in_channels = 4
out_channels = 3
kernel_size = 3
stride = 1
padding = 1
dilation = 1
deformable_groups = 1

# Create DCNv2 module
dcnv2_module = nn.Module()

# Create a tiny input tensor: (batch, in_channels, height, width)
input_tensor = torch.randn(batch_size, in_channels, 8, 8)

# For offset: (batch, deformable_groups * 2 * kernel_size * kernel_size, height_out, width_out)
# height_out = (8 + 2*1 - (1*(3-1)+1)) // 1 + 1 = (10 - 3) // 1 + 1 = 8
offset_tensor = torch.randn(batch_size, deformable_groups * 2 * kernel_size * kernel_size, 8, 8)

# For mask: (batch, deformable_groups * kernel_size * kernel_size, height_out, width_out)
mask_tensor = torch.randn(batch_size, deformable_groups * kernel_size * kernel_size, 8, 8)

ARGS = {
    'in_channels': in_channels,
    'out_channels': out_channels,
    'kernel_size': kernel_size,
    'stride': stride,
    'padding': padding,
    'dilation': dilation,
    'deformable_groups': deformable_groups,
}
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 DCNv2 — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DCNv2 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
center_align Ran
ran on a synthesized input · constructed an object; no result was computed
mumianyuxin/M3DSSD/model/module/feturealign_mgpu.py
code served (permissive licence) · get_code("1d906ba5ec709c00")
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 an instance of its own class, center_align: the run constructed the object and did not call it, so no result was computed. 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 numpy as np

torch.manual_seed(0)

# Small stand-in for anchors tensor
anchors = torch.tensor([
    [10.0, 10.0, 20.0, 20.0],
    [15.0, 15.0, 35.0, 35.0],
    [20.0, 20.0, 50.0, 50.0]
], dtype=torch.float32)

# xy_mean and xy_std for normalization
xy_mean = [0.0, 0.0]
xy_std = [1.0, 1.0]

# Parameters for center_align
ch = 4  # channel dimension
feat_stride = 16  # feature stride
feat_size = (8, 8)  # feature map size (height, width)
kernel_size = 1
k = 1
thresh = 0.5

ARGS = {
    'ch': ch,
    'anchors': anchors,
    'xy_mean': xy_mean,
    'xy_std': xy_std,
    'feat_stride': feat_stride,
    'feat_size': feat_size,
    'kernel_size': kernel_size,
    'k': k,
    'thresh': thresh
}
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 center_align — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a center_align 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
DCNv2Function Not yet run
unverified (harvested, no recorded run)
mumianyuxin/M3DSSD/model/module/feturealign_mgpu.py
code served (permissive licence) · get_code("ae464a472968c2d3")
How it ran

no invocation recorded.

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, 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 1 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
DCNv2
brick of this paper's assembly: helper
1 other paper
1 later
2104.05269 (2021-04)
Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection
DCNv2Function
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2104.05269 (2021-04)
Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection

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

In this paper, we propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. Current anchor-based monocular 3D object detection methods suffer from feature mismatching. To overcome this, we propose a twostep feature alignment approach. In the first step, the shape alignment is performed to enable the receptive field of the feature map to focus on the pre-defined anchors with high confidence scores. In the second step, the center alignment is used to align the features at 2D/3D centers. Further, it is often difficult to learn global information and capture long-range relationships, which are important for the depth prediction of objects. Therefore, we propose a novel asymmetric non-local attention block with multiscale sampling to extract depth-wise features. The proposed M3DSSD achieves significantly better performance than the monocular 3D object detection methods on the KITTI dataset, in both 3D object detection and bird's eye view tasks. The code is released at https://github. com/mumianyuxin/M3DSSD.

For agents

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

get_harvested_code_for_paper("2103.13164")
get_code_for_paper("2103.13164")
have("2103.13164")

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

curl https://syntology.ai/api/ran/2103.13164.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.13164.svg)](https://syntology.ai/paper/2103.13164)

Connect an agent — have() is free.