SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.01054 · 2023

VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 1 has no contract verdict; 4 failures of our instrument; 2 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/2304.01054.json · badge: /api/ran/2304.01054.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
lizhuoling/voxelformer-public canonical (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
lizhuoling/voxelformer-public/projects/mmdet3d_plugin/models/backbones/vovnet.py
code served (permissive licence) · get_code("c637c42a302bb63c")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was 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)

ARGS = {
    'in_channels': 64,
    'out_channels': 128,
    'module_name': 'layer',
    'postfix': 'block1',
    'stride': 1,
    'groups': 1,
    'kernel_size': 1,
    'padding': 0
}
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 list, ndim 2, dtype family float — a list 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
lizhuoling/voxelformer-public/projects/mmdet3d_plugin/models/backbones/vovnet.py
code served (permissive licence) · get_code("303f4d3695ad18f1")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was 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)

ARGS = {
    'in_channels': 3,
    'out_channels': 64,
    'module_name': 'layer',
    'postfix': '0',
    'stride': 1,
    'groups': 1,
    'kernel_size': 3,
    'padding': 1
}
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 list, ndim 2, dtype family float — a list 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
denormalize_bbox Ran
ran on a synthesized input
lizhuoling/voxelformer-public/projects/mmdet3d_plugin/core/bbox/util.py
code served (permissive licence) · get_code("14ddbb72bd9023bf")
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. 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

torch.manual_seed(0)

# Create normalized_bboxes tensor
# Shape: (batch_size, num_features)
# Features: cx, cy, w, l, cz, h, rot_sine, rot_cosine, [vx, vy, uncertainty]
# Testing case with 11 features (includes vx, vy, and uncertainty)
normalized_bboxes = torch.randn(2, 11)

# pc_range defines the point cloud range [x_min, y_min, z_min, x_max, y_max, z_max]
pc_range = [-51.2, -51.2, -5.0, 51.2, 51.2, 3.0]

ARGS = {
    "normalized_bboxes": normalized_bboxes,
    "pc_range": pc_range,
}
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 — a tuple output has no array shape of its own; none is 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
normalize_bbox Ran
ran; our contract draft was wrong, not the code
lizhuoling/voxelformer-public/projects/mmdet3d_plugin/core/bbox/util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sranc3/m-bev, is pointer only (licence: NONE) · get_code("e6ab81c2ff932920")
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 sranc3/m-bev, and GitHub detected no licence in that repository when it was checked. 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.

pos2posemb3d Ran
ran; our contract draft was wrong, not the code
lizhuoling/voxelformer-public/projects/mmdet3d_plugin/models/dense_heads/voxelformer_head.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from HDETR/H-PETR-3D, is pointer only (licence: NOASSERTION) · get_code("718ca707584a0928")
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 HDETR/H-PETR-3D, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

array_converter Not yet run
unverified (harvested, no recorded run)
lizhuoling/voxelformer-public/projects/mmdet3d_plugin/core/bbox/array_converter.py
code served (permissive licence) · get_code("c5537a52f3c7aad0")
How it ran

no invocation recorded.

dw_conv3x3 Not yet run
unverified (harvested, no recorded run)
lizhuoling/voxelformer-public/projects/mmdet3d_plugin/models/backbones/vovnet.py
code served (permissive licence) · get_code("5ebf15e6940f6710")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 6 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
conv1x1 7 other papers
3 dated earlier, 4 later
2110.06923 (2021-10)
Object DGCNN: 3D Object Detection using Dynamic Graphs
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2206.15398 (2022-06)
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
and 4 more not named here
conv3x3 7 other papers
3 dated earlier, 4 later
2110.06923 (2021-10)
Object DGCNN: 3D Object Detection using Dynamic Graphs
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2206.15398 (2022-06)
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
and 4 more not named here
dw_conv3x3 7 other papers
3 dated earlier, 4 later
2110.06923 (2021-10)
Object DGCNN: 3D Object Detection using Dynamic Graphs
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2206.15398 (2022-06)
PolarFormer: Multi-camera 3D Object Detection with Polar Transformer
and 4 more not named here
normalize_bbox 7 other papers
4 dated earlier, 3 later
2110.06923 (2021-10)
Object DGCNN: 3D Object Detection using Dynamic Graphs
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
2205.13542 (2022-05)
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
and 4 more not named here
pos2posemb3d 6 other papers
2 dated earlier, 4 later
2206.01256 (2022-06)
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
2207.13080 (2022-07)
DETRs with Hybrid Matching
2308.04583 (2023-08)
LATR: 3D Lane Detection from Monocular Images with Transformer
and 3 more not named here
array_converter 3 other papers
1 the same month, 2 later
2304.14365 (2023-04)
Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
2312.12144 (2023-12)
M-BEV: Masked BEV Perception for Robust Autonomous Driving
2407.10876 (2024-07)
RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception

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 recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks. However, their performance in multi-view 3D object detection remains inferior to the state-of-the-art (SOTA) of convolutional neural network based detectors. In this work, we investigate this issue from the perspective of bird's-eye-view (BEV) feature generation. Specifically, we examine the BEV feature generation method employed by the transformer-based SOTA, BEVFormer, and identify its two limitations: (i) it only generates attention weights from BEV, which precludes the use of lidar points for supervision, and (ii) it aggregates camera view features to the BEV through deformable sampling, which only selects a small subset of features and fails to exploit all information. To overcome these limitations, we propose a novel BEV feature generation method, dual-view attention, which generates attention weights from both the BEV and camera view. This method encodes all camera features into the BEV feature. By combining dual-view attention with the BEVFormer architecture, we build a new detector named VoxelFormer. Extensive experiments are conducted on the nuScenes benchmark to verify the superiority of dual-view attention and VoxelForer. We observe that even only adopting 3 encoders and 1 historical frame during training, VoxelFormer still outperforms BEVFormer significantly. When trained in the same setting, VoxelFormer can surpass BEVFormer by 4.9% NDS point. Code is available at: https://github.com/Lizhuoling/VoxelFormer-public.git.

For agents

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

get_harvested_code_for_paper("2304.01054")
get_code_for_paper("2304.01054")
have("2304.01054")

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

curl https://syntology.ai/api/ran/2304.01054.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.01054.svg)](https://syntology.ai/paper/2304.01054)

Connect an agent — have() is free.