SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.05327 · 2024

DiffSF: Diffusion Models for Scene Flow Estimation

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 9 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/2403.05327.json · badge: /api/ran/2403.05327.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
zhangyushan3/diffsf canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
flip_point_cloud Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhangyushan3/diffsf/datasetloader/augmentation.py
pointer only (licence: NONE) · get_code("21e4495ad40554c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

flip_scene_flow Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhangyushan3/diffsf/datasetloader/augmentation.py
pointer only (licence: NONE) · get_code("c1a1a3e037cf14ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

get_graph_feature Ran
ran; our contract draft was wrong, not the code
zhangyushan3/diffsf/models/backbone.py
pointer only (licence: NONE) · get_code("6106815f95a68b0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

global_selfcorrelation_softmax_3d Ran
ran on a synthesized input
zhangyushan3/diffsf/models/matching.py
pointer only (licence: NONE) · get_code("e9e4f2880167194f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

index_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhangyushan3/diffsf/models/transformer.py
pointer only (licence: NONE) · get_code("60d47f425d9acbaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhangyushan3/diffsf/models/backbone.py
pointer only (licence: NONE) · get_code("cdd0141594039dcb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

random_flip_pc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhangyushan3/diffsf/datasetloader/augmentation.py
pointer only (licence: NONE) · get_code("a927fe2691f83c7f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

sceneflow_loss_func Ran
ran; our contract draft was wrong, not the code
zhangyushan3/diffsf/loss/sceneflow_loss.py
pointer only (licence: NONE) · get_code("0630a3b50052e0b9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

single_head_full_attention Ran
ran; our contract draft was wrong, not the code
zhangyushan3/diffsf/models/transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from ispc-lab/tma, is pointer only (licence: NONE) · get_code("52b500940a8025a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

square_distance Ran
ran; our contract draft was wrong, not the code
zhangyushan3/diffsf/models/transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from ORCA-Uboat/RadarMOSEVE, is pointer only (licence: NONE) · get_code("74c3fe06cea2f553")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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.

global_correlation_softmax_3d Not yet run
unverified (harvested, no recorded run)
zhangyushan3/diffsf/models/matching.py
pointer only (licence: NONE) · get_code("4804a1a5fbed9945")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhangyushan3/diffsf 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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 3 later) and 5 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
knn 52 other papers
39 dated earlier, 4 the same month, 9 later · 12 only as an assembly brick
1801.07829 (2018-01)
Dynamic Graph CNN for Learning on Point Clouds
1905.06292 (2019-05)
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
2005.06734 (2020-05)
Dense-Resolution Network for Point Cloud Classification and Segmentation
and 49 more not named here
square_distance 14 other papers
10 dated earlier, 4 later · 1 only as an assembly brick
2110.11860 (2021-10)
AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations
2203.06604 (2022-03)
Masked Autoencoders for Point Cloud Self-supervised Learning
and 11 more not named here
single_head_full_attention 6 other papers
2 dated earlier, 4 later
2111.13680 (2021-11)
GMFlow: Learning Optical Flow via Global Matching
2303.11629 (2023-03)
TMA: Temporal Motion Aggregation for Event-based Optical Flow
2409.16288 (2024-09)
Self-Supervised Any-Point Tracking by Contrastive Random Walks
and 3 more not named here
flip_point_cloud 1 other paper
1 dated earlier
2402.18146 (2024-02)
3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling
flip_scene_flow 1 other paper
1 dated earlier
2402.18146 (2024-02)
3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling
random_flip_pc 1 other paper
1 dated earlier
2402.18146 (2024-02)
3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling

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 is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy, their applicability to real-world systems additionally benefits from a reliability measure. Aiming at improving accuracy while additionally providing an estimate for uncertainty, we propose DiffSF that combines transformer-based scene flow estimation with denoising diffusion models. In the diffusion process, the ground truth scene flow vector field is gradually perturbed by adding Gaussian noise. In the reverse process, starting from randomly sampled Gaussian noise, the scene flow vector field prediction is recovered by conditioning on a source and a target point cloud. We show that the diffusion process greatly increases the robustness of predictions compared to prior approaches resulting in state-of-the-art performance on standard scene flow estimation benchmarks. Moreover, by sampling multiple times with different initial states, the denoising process predicts multiple hypotheses, which enables measuring the output uncertainty, allowing our approach to detect a majority of the inaccurate predictions. The code is available at https://github.com/ZhangYushan3/DiffSF.

For agents

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

get_harvested_code_for_paper("2403.05327")
get_code_for_paper("2403.05327")
have("2403.05327")

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

curl https://syntology.ai/api/ran/2403.05327.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.05327.svg)](https://syntology.ai/paper/2403.05327)

Connect an agent — have() is free.