SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.10353 · ECCV · 2024

SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras

Guoliang Chen, Yingqi Tang, Zhaotie Meng, Erkang Cheng

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2403.10353.json · badge: /api/ran/2403.10353.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
nullmax-vision/SimPB canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_reference_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nullmax-vision/SimPB/projects/mmdet3d_plugin/models/utils.py
code served (permissive licence) · get_code("6515dd44533e4a2b")
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 Tensor, ndim 4, dtype family float, shape (2, 26, 2, 2) 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

torch.manual_seed(0)

# spatial_shapes: list of (H, W) tuples for different feature levels
spatial_shapes = [(4, 5), (2, 3)]

# valid_ratios: tensor of shape (batch_size, num_levels, 2)
# batch_size=2, num_levels=2, last dim is (width_ratio, height_ratio)
valid_ratios = torch.tensor([
    [[1.0, 1.0], [1.0, 1.0]],
    [[0.9, 0.95], [0.85, 0.9]]
], dtype=torch.float32)

# device
device = 'cpu'

ARGS = {
    'spatial_shapes': spatial_shapes,
    'valid_ratios': valid_ratios,
    'device': device
}
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 Tensor, ndim 4, dtype family float, shape (2, 26, 2, 2) — shape (2, 26, 2, 2) 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_valid_ratio Ran
ran, honoured the contract we drafted
nullmax-vision/SimPB/projects/mmdet3d_plugin/models/utils.py
code served (permissive licence) · get_code("aef7b421ef8bf22e")
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 Tensor, ndim 2, dtype family float, shape (2, 2) 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

torch.manual_seed(0)

# The function expects a mask tensor with shape (batch, H, W)
# where mask is a boolean tensor (or something that supports ~mask for bitwise NOT)
# The function accesses:
# - mask.shape to get _, H, W
# - mask[:, :, 0] to get all elements at W index 0
# - mask[:, 0, :] to get all elements at H index 0
# - ~mask to negate boolean values

# Create a small mask tensor with shape (batch=2, H=4, W=3)
mask = torch.zeros((2, 4, 3), dtype=torch.bool)

# Make some parts True to have variation in valid ratios
mask[0, 0:2, :] = True  # First batch, first 2 rows are masked
mask[1, 0:1, :] = True  # Second batch, first row is masked

ARGS = {
    "mask": mask
}
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 Tensor, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) 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
inverse_sigmoid Ran
ran; our contract draft was wrong, not the code
nullmax-vision/SimPB/projects/mmdet3d_plugin/models/group_attn.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from woodfrog/poly-diffuse, is pointer only (licence: GPL-3.0) · get_code("83c03ceb1307c6c4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from woodfrog/poly-diffuse, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

topk Not yet run
unverified (harvested, no recorded run)
nullmax-vision/SimPB/projects/mmdet3d_plugin/models/instance_bank.py
code served (permissive licence) · get_code("82c79d0ad5cc7f82")
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, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 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
inverse_sigmoid 51 other papers
39 dated earlier, 2 the same month, 9 later, 1 same year, order not determinable · 23 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11161 (2021-03)
MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
and 48 more not named here
topk 3 other papers
3 later
2405.19620 (2024-05)
SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation
2503.03125 (2025-03)
Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving
get_valid_ratio 2 other papers
2 dated earlier
2005.10821 (2020-05)
Hierarchical Multi-Scale Attention for Semantic Segmentation
2303.17783 (2023-03)
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer

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 field of autonomous driving has attracted considerable interest in approaches that directly infer 3D objects in the Bird's Eye View (BEV) from multiple cameras. Some attempts have also explored utilizing 2D detectors from single images to enhance the performance of 3D detection. However, these approaches rely on a two-stage process with separate detectors, where the 2D detection results are utilized only once for token selection or query initialization. In this paper, we present a single model termed SimPB, which Simultaneously detects 2D objects in the Perspective view and 3D objects in the BEV space from multiple cameras. To achieve this, we introduce a hybrid decoder consisting of several multiview 2D decoder layers and several 3D decoder layers, specifically designed for their respective detection tasks. A Dynamic Query Allocation module and an Adaptive Query Aggregation module are proposed to continuously update and refine the interaction between 2D and 3D results, in a cyclic 3D-2D-3D manner. Additionally, Query-group Attention is utilized to strengthen the interaction among 2D queries within each camera group. In the experiments, we evaluate our method on the nuScenes dataset and demonstrate promising results for both 2D and 3D detection tasks. Our code is available at: https://github.com/nullmax-vision/SimPB.

For agents

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

get_harvested_code_for_paper("2403.10353")
get_code_for_paper("2403.10353")
have("2403.10353")

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

curl https://syntology.ai/api/ran/2403.10353.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.10353.svg)](https://syntology.ai/paper/2403.10353)

Connect an agent — have() is free.