SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16895 · CVPR · 2022

Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds

Munawar Hayat, Naveed Akhtar, Zhao Jin, Haifeng Li, Yinjie Lei

arXiv · PDF · Open in the Atlas

Code that ran

3 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 3 have no contract verdict; 0 failures of our instrument; 4 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/2203.16895.json · badge: /api/ran/2203.16895.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
leolyj/DCA-SRSFE community
Papers with Code archive
3 ran · 4 no recorded run
FunctionStatusWhere it lives
Conv1dReLU Ran
ran on a synthesized input
leolyj/DCA-SRSFE/models/HPLFlowNet.py
code served (permissive licence) · get_code("8b08a81d5ff89ab2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 5) 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
import torch.nn as nn

LEAKY_RATE = 0.1

class Conv1dReLU(nn.Module):

    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, use_leaky=False, bias=True):
        super(Conv1dReLU, self).__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        relu = nn.ReLU(inplace=False) if not use_leaky else nn.LeakyReLU(LEAKY_RATE, inplace=False)
        self.composed_module = nn.Sequential(nn.Conv1d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias), relu)

    def forward(self, x):
        x = self.composed_module(x)
        return x


INIT_ARGS = {
    'in_channels': 4,
    'out_channels': 3,
    'kernel_size': 1,
    'stride': 1,
    'padding': 0,
    'use_leaky': False,
    'bias': True
}

ARGS = {
    'x': torch.randn(2, 4, 5)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 3, dtype family float, shape (2, 3, 5) — shape (2, 3, 5) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Conv2dReLU Ran
ran on a synthesized input
leolyj/DCA-SRSFE/models/HPLFlowNet.py
code served (permissive licence) · get_code("60ee761c0635e47c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 8, 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
import torch.nn as nn

LEAKY_RATE = 0.1

class Conv2dReLU(nn.Module):

    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, use_leaky=False, bias=True):
        super(Conv2dReLU, self).__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        relu = nn.ReLU(inplace=False) if not use_leaky else nn.LeakyReLU(LEAKY_RATE, inplace=False)
        self.composed_module = nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias), relu)

    def forward(self, x):
        x = self.composed_module(x)
        return x


INIT_ARGS = {
    'in_channels': 3,
    'out_channels': 4,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'use_leaky': False,
    'bias': True
}

ARGS = {
    'x': torch.randn(2, 3, 8, 8)
}

if __name__ == '__main__':
    model = Conv2dReLU(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Output dtype: {output.dtype}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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, 4, 8, 8) — shape (2, 4, 8, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Conv3dReLU Ran
ran on a synthesized input
leolyj/DCA-SRSFE/models/HPLFlowNet.py
code served (permissive licence) · get_code("584b8fc486073bb0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 5, dtype family float, shape (2, 4, 5, 6, 7) 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
import torch.nn as nn

LEAKY_RATE = 0.1

class Conv3dReLU(nn.Module):

    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, use_leaky=False, bias=True):
        super(Conv3dReLU, self).__init__()
        relu = nn.ReLU(inplace=False) if not use_leaky else nn.LeakyReLU(LEAKY_RATE, inplace=False)
        self.composed_module = nn.Sequential(nn.Conv3d(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias), relu)

    def forward(self, x):
        x = self.composed_module(x)
        return x


INIT_ARGS = {
    'in_channels': 3,
    'out_channels': 4,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'use_leaky': False,
    'bias': True
}

ARGS = {
    'x': torch.randn(2, 3, 5, 6, 7)
}

if __name__ == '__main__':
    model = Conv3dReLU(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: (2, 4, 5, 6, 7)")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 5, dtype family float, shape (2, 4, 5, 6, 7) — shape (2, 4, 5, 6, 7) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
BilateralConvFlex Not yet run
unverified (harvested, no recorded run)
leolyj/DCA-SRSFE/models/HPLFlowNet.py
code served (permissive licence) · get_code("f9368771214eaf8c")
How it ran

no invocation recorded.

BilateralCorrelationFlex Not yet run
unverified (harvested, no recorded run)
leolyj/DCA-SRSFE/models/HPLFlowNet.py
code served (permissive licence) · get_code("38fa0953b57b7b55")
How it ran

no invocation recorded.

HPLFlowNet Not yet run
unverified (harvested, no recorded run)
leolyj/DCA-SRSFE/models/HPLFlowNet.py
code served (permissive licence) · get_code("2fef1e091753f845")
How it ran

no invocation recorded.

SparseSum Not yet run
unverified (harvested, no recorded run)
leolyj/DCA-SRSFE/models/HPLFlowNet.py
code served (permissive licence) · get_code("46d86f26661026b7")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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.

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

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real scenes. However, large disparities between existing synthetic datasets and real scenes lead to poor model transfer. We make two major contributions to address that. First, we develop a point cloud collector and scene flow annotator for GTA-V engine to automatically obtain diverse realistic training samples without human intervention. With that, we develop a large-scale synthetic scene flow dataset GTA-SF. Second, we propose a mean-teacher-based domain adaptation framework that leverages self-generated pseudo-labels of the target domain. It also explicitly incorporates shape deformation regularization and surface correspondence refinement to address distortions and misalignments in domain transfer. Through extensive experiments, we show that our GTA-SF dataset leads to a consistent boost in model generalization to three real datasets (i.e., Waymo, Lyft and KITTI) as compared to the most widely used FT3D dataset. Moreover, our framework achieves superior adaptation performance on six source-target dataset pairs, remarkably closing the average domain gap by 60%. Data and codes are available at https://github.com/leolyj/DCA-SRSFE

For agents

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

get_harvested_code_for_paper("2203.16895")
get_code_for_paper("2203.16895")
have("2203.16895")

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

curl https://syntology.ai/api/ran/2203.16895.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.16895.svg)](https://syntology.ai/paper/2203.16895)

Connect an agent — have() is free.