SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.10876 · ECCV · 2024

RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception

Junbo Yin, Wencheng Han, Jianbing Shen, Sanyuan Zhao, Chunliang Li

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 0 have 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/2407.10876.json · badge: /api/ran/2407.10876.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
jbji/RepVF canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
jbji/RepVF/plugins/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
jbji/RepVF/plugins/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; our contract draft was wrong, not the code
jbji/RepVF/plugins/core/bbox/util.py
code served (permissive licence) · get_code("b8cdf4cad83ce917")
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, 8) 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)

# Create a small normalized bboxes tensor
# Shape: (batch_size=2, num_features=9)
# Features: [cx, cy, w, l, cz, h, rot_sine, rot_cosine, vx, vy]
# Last 2 features (vx, vy) test the conditional branch for velocities
normalized_bboxes = torch.tensor([
    [0.5, 0.3, 0.1, 0.2, 0.4, 0.15, 0.1, 0.9, 0.05],
    [0.6, 0.4, 0.12, 0.25, 0.5, 0.18, 0.2, 0.95, 0.08]
], dtype=torch.float32)

# pc_range is optional and not used in the function body
pc_range = None

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 Tensor, ndim 2, dtype family float, shape (2, 8) — shape (2, 8) 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
normalize_bbox Ran
ran; our contract draft was wrong, not the code
jbji/RepVF/plugins/core/bbox/util.py
code served (permissive licence) · get_code("8800486c70b30b88")
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, 10) 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)

# Create a small bboxes tensor with shape (2, 9)
# Dimensions: [cx, cy, cz, w, l, h, rot, vx, vy]
# Need positive values for w, l, h since they will be log'd
bboxes = torch.tensor([
    [0.5, 1.0, 2.0, 0.8, 1.2, 0.6, 0.5, 0.1, 0.2],
    [1.5, 2.0, 3.0, 1.0, 1.5, 0.9, 1.0, 0.3, 0.4]
], dtype=torch.float32)

ARGS = {
    "bboxes": bboxes,
    "pc_range": None
}
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, 10) — shape (2, 10) 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
array_converter Not yet run
unverified (harvested, no recorded run)
jbji/RepVF/plugins/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)
jbji/RepVF/plugins/models/backbones/vovnet.py
code served (permissive licence) · get_code("5ebf15e6940f6710")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 0 later) and 0 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
6 dated earlier, 1 the same month
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
6 dated earlier, 1 the same month
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
6 dated earlier, 1 the same month
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
array_converter 3 other papers
3 dated earlier
2304.01054 (2023-04)
VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
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
denormalize_bbox 1 other paper
1 dated earlier
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
normalize_bbox 1 other paper
1 dated earlier
2203.10642 (2022-03)
FUTR3D: A Unified Sensor Fusion Framework for 3D 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

Concurrent processing of multiple autonomous driving 3D perception tasks within the same spatiotemporal scene poses a significant challenge, in particular due to the computational inefficiencies and feature competition between tasks when using traditional multi-task learning approaches. This paper addresses these issues by proposing a novel unified representation, RepVF, which harmonizes the representation of various perception tasks such as 3D object detection and 3D lane detection within a single framework. RepVF characterizes the structure of different targets in the scene through a vector field, enabling a singlehead, multi-task learning model that significantly reduces computational redundancy and feature competition. Building upon RepVF, we introduce RFTR, a network designed to exploit the inherent connections between different tasks by utilizing a hierarchical structure of queries that implicitly model the relationships both between and within tasks. This approach eliminates the need for task-specific heads and parameters, fundamentally reducing the conflicts inherent in traditional multi-task learning paradigms. We validate our approach by combining labels from the OpenLane dataset with the Waymo Open dataset. Our work presents a significant advancement in the efficiency and effectiveness of multi-task perception in autonomous driving, offering a new perspective on handling multiple 3D perception tasks synchronously and in parallel. The code will be available at: https://github.com/jbji/RepVF.

For agents

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

get_harvested_code_for_paper("2407.10876")
get_code_for_paper("2407.10876")
have("2407.10876")

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

curl https://syntology.ai/api/ran/2407.10876.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.10876.svg)](https://syntology.ai/paper/2407.10876)

Connect an agent — have() is free.