SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.01702 · ECCV · 2024

SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving

Yi Yang, Qingwen Zhang, Olov Andersson, Patric Jensfelt, Peizheng Li

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 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/2407.01702.json · badge: /api/ran/2407.01702.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
KTH-RPL/SeFlow canonical (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
deflowLoss Ran
ran; our contract draft was wrong, not the code
KTH-RPL/SeFlow/lossfunc.py
code served (permissive licence) · get_code("133aec51ee5b1a44")
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 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

torch.manual_seed(0)

# Create small tensors for flow data
# The function expects tensors with shape that can be reshaped to (-1, 3)
# Let's create 2D flow tensors: batch_size x height x width x 3

batch_size = 2
height = 2
width = 2
channels = 3

# Create estimated flow tensor
est_flow = torch.randn(batch_size, height, width, channels)

# Create ground truth flow tensor with some valid values
gt_flow = torch.randn(batch_size, height, width, channels)

# Create the result dictionary that the function expects
res_dict = {
    'est_flow': est_flow,
    'gt_flow': gt_flow
}

ARGS = {
    'res_dict': res_dict
}
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 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
zeroflowLoss Ran
ran; our contract draft was wrong, not the code
KTH-RPL/SeFlow/lossfunc.py
code served (permissive licence) · get_code("82ca3787fafa7371")
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 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

torch.manual_seed(0)

# Create sample tensors for flow data
# Shape: (batch, height, width, 3) where 3 is for (x, y, z) flow components
batch_size = 2
height = 4
width = 4
channels = 3

# Create estimated flow (pred)
est_flow = torch.randn(batch_size, height, width, channels)

# Create ground truth flow (gt)
gt_flow = torch.randn(batch_size, height, width, channels)

# Create the result dictionary that the function expects
res_dict = {
    'est_flow': est_flow,
    'gt_flow': gt_flow
}

ARGS = {
    'res_dict': res_dict
}
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 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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
deflowLoss 2 other papers
1 dated earlier, 1 later
2401.16122 (2024-01)
DeFlow: Decoder of Scene Flow Network in Autonomous Driving
2508.18506 (2025-08)
DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance
zeroflowLoss 2 other papers
1 dated earlier, 1 later
2401.16122 (2024-01)
DeFlow: Decoder of Scene Flow Network in Autonomous Driving
2508.18506 (2025-08)
DoGFlow: Self-Supervised LiDAR Scene Flow via Cross-Modal Doppler Guidance

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

Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current state-of-the-art methods require annotated data to train scene flow networks and the expense of labeling inherently limits their scalability. Self-supervised approaches can overcome the above limitations, yet face two principal challenges that hinder optimal performance: point distribution imbalance and disregard for object-level motion constraints. In this paper, we propose SeFlow, a selfsupervised method that integrates efficient dynamic classification into a learning-based scene flow pipeline. We demonstrate that classifying static and dynamic points helps design targeted objective functions for different motion patterns. We also emphasize the importance of internal cluster consistency and correct object point association to refine the scene flow estimation, in particular on object details. Our real-time capable method achieves state-of-the-art performance on the self-supervised scene flow task on Argoverse 2 and Waymo datasets. The code is opensourced at https://github.com/KTH-RPL/SeFlow.

For agents

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

get_harvested_code_for_paper("2407.01702")
get_code_for_paper("2407.01702")
have("2407.01702")

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

curl https://syntology.ai/api/ran/2407.01702.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.01702.svg)](https://syntology.ai/paper/2407.01702)

Connect an agent — have() is free.