SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.11335 · CVPR · 2022

Global Matching with Overlapping Attention for Optical Flow Estimation

Long Zhao, Dimitris Metaxas, Shiyu Zhao, Enyu Zhou, Zhixing Zhang

arXiv · PDF · Open in the Atlas

Code that ran

7 of 14 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 5 have no contract verdict; 2 failures of our instrument; 7 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/2203.11335.json · badge: /api/ran/2203.11335.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
xiaofeng94/gmflownet marked official in Papers with Code
Papers with Code archive
7 ran · 7 no recorded run
FunctionStatusWhere it lives
BasicConvEncoder Ran
ran on a synthesized input
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("609f6aa177f73bc1")
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, 128, 4, 4) 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
import torch.nn.functional as F

class BasicConvEncoder(nn.Module):
    """docstring for BasicConvEncoder"""

    def __init__(self, output_dim=128, norm_fn='batch', dropout=0.0):
        super(BasicConvEncoder, self).__init__()
        self.norm_fn = norm_fn
        half_out_dim = max(output_dim // 2, 64)
        if self.norm_fn == 'group':
            self.norm1 = nn.GroupNorm(num_groups=8, num_channels=64)
            self.norm2 = nn.GroupNorm(num_groups=8, num_channels=64)
            self.norm3 = nn.GroupNorm(num_groups=8, num_channels=64)
        elif self.norm_fn == 'batch':
            self.norm1 = nn.BatchNorm2d(64)
            self.norm2 = nn.BatchNorm2d(half_out_dim)
            self.norm3 = nn.BatchNorm2d(output_dim)
        elif self.norm_fn == 'instance':
            self.norm1 = nn.InstanceNorm2d(64)
            self.norm2 = nn.InstanceNorm2d(half_out_dim)
            self.norm3 = nn.InstanceNorm2d(output_dim)
        elif self.norm_fn == 'none':
            self.norm1 = nn.Sequential()
            self.norm2 = nn.Sequential()
            self.norm3 = nn.Sequential()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
        self.conv2 = nn.Conv2d(64, half_out_dim, kernel_size=3, stride=2, padding=1)
        self.conv3 = nn.Conv2d(half_out_dim, output_dim, kernel_size=3, stride=2, padding=1)
        self.dropout = None
        if dropout > 0:
            self.dropout = nn.Dropout2d(p=dropout)

    def forward(self, x):
        is_list = isinstance(x, tuple) or isinstance(x, list)
        if is_list:
            batch_dim = x[0].shape[0]
            x = torch.cat(x, dim=0)
        x = F.relu(self.norm1(self.conv1(x)), inplace=True)
        x = F.relu(self.norm2(self.conv2(x)), inplace=True)
        x = F.relu(self.norm3(self.conv3(x)), inplace=True)
        if self.training and self.dropout is not None:
            x = self.dropout(x)
        if is_list:
            x = torch.split(x, [batch_dim, batch_dim], dim=0)
        return x


INIT_ARGS = {
    'output_dim': 128,
    'norm_fn': 'batch',
    'dropout': 0.0,
}

ARGS = {
    'x': torch.randn(2, 3, 32, 32),
}

if __name__ == '__main__':
    model = BasicConvEncoder(**INIT_ARGS)
    model.eval()
    output = model(**ARGS)
    print("Output shape:", output.shape)
    print("Test passed!")
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, 128, 4, 4) — shape (2, 128, 4, 4) 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)
BasicMotionEncoder Ran
ran on a synthesized input
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("782c69df771932e7")
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; 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 numpy as np
from types import SimpleNamespace

# INIT_ARGS for BasicMotionEncoder.__init__
INIT_ARGS = {
    "args": SimpleNamespace(
        motion_feat_indim=4,  # small stand-in for cor_planes
        corr_levels=1,        # unused when motion_feat_indim is provided
        corr_radius=1         # unused when motion_feat_indim is provided
    )
}

# ARGS for BasicMotionEncoder.forward
flow = torch.randn(2, 2, 4, 3)  # batch=2, channels=2, height=4, width=3
corr = torch.randn(2, 4, 4, 3)  # batch=2, cor_planes=4, height=4, width=3

ARGS = {
    "flow": flow,
    "corr": corr
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, 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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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)
CorrBlock Ran
ran on a synthesized input
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("061bb91459aa0019")
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, 50, 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.functional as F

def bilinear_sampler(img, coords, mode='bilinear', mask=False):
    """ Wrapper for grid_sample, uses pixel coordinates """
    H, W = img.shape[-2:]
    xgrid, ygrid = coords.split([1, 1], dim=-1)
    xgrid = 2 * xgrid / (W - 1) - 1
    ygrid = 2 * ygrid / (H - 1) - 1
    grid = torch.cat([xgrid, ygrid], dim=-1)
    img = F.grid_sample(img, grid, align_corners=True)
    if mask:
        mask = (xgrid > -1) & (ygrid > -1) & (xgrid < 1) & (ygrid < 1)
        return (img, mask.float())
    return img

class CorrBlock:

    def __init__(self, fmap1, fmap2, num_levels=4, radius=4):
        self.num_levels = num_levels
        self.radius = radius
        self.corr_pyramid = []
        corr = CorrBlock.corr(fmap1, fmap2)
        batch, h1, w1, dim, h2, w2 = corr.shape
        self.corrMap = corr.view(batch, h1 * w1, h2 * w2)
        corr = corr.reshape(batch * h1 * w1, dim, h2, w2)
        self.corr_pyramid.append(corr)
        for i in range(self.num_levels - 1):
            corr = F.avg_pool2d(corr, 2, stride=2)
            self.corr_pyramid.append(corr)

    def __call__(self, coords):
        r = self.radius
        coords = coords.permute(0, 2, 3, 1)
        batch, h1, w1, _ = coords.shape
        out_pyramid = []
        for i in range(self.num_levels):
            corr = self.corr_pyramid[i]
            dx = torch.linspace(-r, r, 2 * r + 1)
            dy = torch.linspace(-r, r, 2 * r + 1)
            delta = torch.stack(torch.meshgrid(dy, dx), dim=-1).to(coords.device)
            centroid_lvl = coords.reshape(batch * h1 * w1, 1, 1, 2) / 2 ** i
            delta_lvl = delta.view(1, 2 * r + 1, 2 * r + 1, 2)
            coords_lvl = centroid_lvl + delta_lvl
            corr = bilinear_sampler(corr, coords_lvl)
            corr = corr.view(batch, h1, w1, -1)
            out_pyramid.append(corr)
        out = torch.cat(out_pyramid, dim=-1)
        return out.permute(0, 3, 1, 2).contiguous().float()

    @staticmethod
    def corr(fmap1, fmap2):
        batch, dim, ht, wd = fmap1.shape
        fmap1 = fmap1.view(batch, dim, ht * wd)
        fmap2 = fmap2.view(batch, dim, ht * wd)
        corr = torch.matmul(fmap1.transpose(1, 2), fmap2)
        corr = corr.view(batch, ht, wd, 1, ht, wd)
        return corr / torch.sqrt(torch.tensor(dim).float())


# Setup code
batch_size = 2
dim = 4
height = 3
width = 5

fmap1 = torch.randn(batch_size, dim, height, width)
fmap2 = torch.randn(batch_size, dim, height, width)

INIT_ARGS = {
    'fmap1': fmap1,
    'fmap2': fmap2,
    'num_levels': 2,
    'radius': 2,
}

coords = torch.randn(batch_size, 2, height, width) * 2 + height / 2

ARGS = {
    'coords': coords,
}

METHOD = '__call__'

# Construct and call
corr_block = CorrBlock(**INIT_ARGS)
output = corr_block(**ARGS)
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, 50, 3, 5) — shape (2, 50, 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)
DropPath Ran
ran on a synthesized input
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("b20207e9c582c326")
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, 4, 3) 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

def drop_path(x, drop_prob: float=0.0, training: bool=False, scale_by_keep: bool=True):
    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
    'survival rate' as the argument.

    """
    if drop_prob == 0.0 or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)
    random_tensor = x.new_empty(shape).bernoulli_(keep_prob)
    if keep_prob > 0.0 and scale_by_keep:
        random_tensor.div_(keep_prob)
    return x * random_tensor

class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """

    def __init__(self, drop_prob: float=0.0, scale_by_keep: bool=True):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob
        self.scale_by_keep = scale_by_keep

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training, self.scale_by_keep)


INIT_ARGS = {
    'drop_prob': 0.2,
    'scale_by_keep': True,
}

ARGS = {
    'x': torch.randn(2, 4, 3),
}

if __name__ == '__main__':
    model = DropPath(**INIT_ARGS)
    model.train()
    output = model(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Output:\n{output}")
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, 4, 3) — shape (2, 4, 3) 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)
MultiHeadAttention Ran
ran on a synthesized input
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("ca7156b5b0317a60")
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 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
import torch.nn as nn
import torch.nn.functional as F
import math

class MultiHeadAttention(nn.Module):
    """ Multi-Head Attention module """

    def __init__(self, d_model, n_head, dropout=0.1):
        super().__init__()
        assert d_model % n_head == 0
        self.n_head = n_head
        self.d_model = d_model
        self.d_head = self.d_model // self.n_head
        self.w_qs = nn.Linear(self.d_model, self.d_model, bias=False)
        self.w_ks = nn.Linear(self.d_model, self.d_model, bias=False)
        self.w_vs = nn.Linear(self.d_model, self.d_model, bias=False)
        self.fc = nn.Linear(self.d_model, self.d_model)
        self.dropout = nn.Dropout(dropout)

    def forward(self, q, k, v):
        """ 
           q: shape of N*len*C
        """
        d_head, n_head = (self.d_head, self.n_head)
        sz_b, len_q, len_k, len_v = (q.size(0), q.size(1), k.size(1), v.size(1))
        q = self.w_qs(q).view(sz_b, len_q, n_head, d_head)
        k = self.w_ks(k).view(sz_b, len_k, n_head, d_head)
        v = self.w_vs(v).view(sz_b, len_v, n_head, d_head)
        q, k, v = (q.transpose(1, 2), k.transpose(1, 2), v.transpose(1, 2))
        attn = torch.matmul(q, k.transpose(-1, -2)) / math.sqrt(self.d_head)
        attn = self.dropout(F.softmax(attn, dim=-1))
        q_updated = torch.matmul(attn, v)
        q_updated = q_updated.transpose(1, 2).contiguous().view(sz_b, len_q, -1)
        q_updated = self.dropout(self.fc(q_updated))
        return (q_updated, attn)


INIT_ARGS = {
    'd_model': 8,
    'n_head': 2,
    'dropout': 0.1
}

ARGS = {
    'q': torch.randn(2, 3, 8),
    'k': torch.randn(2, 5, 8),
    'v': torch.randn(2, 5, 8)
}

if __name__ == '__main__':
    model = MultiHeadAttention(**INIT_ARGS)
    output, attention = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Attention shape: {attention.shape}")
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 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("0c29759c872834a2")
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) and returned Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) 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 input tensor with shape (B, H, W, C)
# B=2 (batch), H=8 (height), W=8 (width), C=4 (channels)
# Using window_size=4, so H and W must be divisible by window_size
x = torch.randn(2, 8, 8, 4)

# window_size must divide both H and W evenly
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (8, 4, 4, 4) — shape (8, 4, 4, 4) 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
window_reverse Ran
ran; our contract draft was wrong, not the code
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("15f7f0358ef0fbda")
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) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 8, 3) 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)

# Parameters for window_reverse
# windows: (num_windows*B, window_size, window_size, C)
# The function expects windows to be partitioned into patches
# Let's use: B=2, window_size=4, H=8, W=8, C=3
# num_windows = (H/window_size) * (W/window_size) = 2*2 = 4
# So windows.shape[0] = num_windows*B = 4*2 = 8

B = 2
window_size = 4
H = 8
W = 8
C = 3

num_windows = (H // window_size) * (W // window_size)
windows = torch.randn(num_windows * B, window_size, window_size, C)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 8, 8, 3) — shape (2, 8, 8, 3) 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
BasicUpdateBlock Not yet run
unverified (harvested, no recorded run)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("8025ceaeea5ca5a2")
How it ran

no invocation recorded.

GMFlowNetModel Not yet run
unverified (harvested, no recorded run)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("0ae44dff0ca3040c")
How it ran

no invocation recorded.

MixAxialPOLABlock Not yet run
unverified (harvested, no recorded run)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("61d28a70c06c21d7")
How it ran

no invocation recorded.

MixAxialPOLAUpdate Not yet run
unverified (harvested, no recorded run)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("2a65e60045482a36")
How it ran

no invocation recorded.

NeighborWindowAttention Not yet run
unverified (harvested, no recorded run)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("a189f54d1c241ec9")
How it ran

no invocation recorded.

POLATransBlock Not yet run
unverified (harvested, no recorded run)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("af3847d6a9584d02")
How it ran

no invocation recorded.

POLAUpdate Not yet run
unverified (harvested, no recorded run)
xiaofeng94/gmflownet/core/gmflownet_model.py
code served (permissive licence) · get_code("673740b96395b8cf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 3 later) and 11 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
window_reverse
brick of this paper's assembly: helper
227 other papers
33 dated earlier, 11 the same month, 181 later, 2 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition
brick of this paper's assembly: helper
223 other papers
31 dated earlier, 10 the same month, 180 later, 2 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
DropPath
brick of this paper's assembly: helper
3 other papers
3 later
2304.03435 (2023-04)
Towards Unified Scene Text Spotting based on Sequence Generation
2407.04619 (2024-07)
COUNTGD: Multi-Modal Open-World Counting
2601.06793 (2026-01)
CliffordNet: All You Need is Geometric Algebra

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

Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion correspondences and thus cannot handle large motions effectively. In this paper, inspired by the traditional matching-optimization methods where matching is introduced to handle large displacements before energy-based optimizations, we introduce a simple but effective global matching step before the direct regression and develop a learning-based matching-optimization framework, namely GMFlowNet. In GMFlowNet, global matching is efficiently calculated by applying argmax on 4D cost volumes. Additionally, to improve the matching quality, we propose patch-based overlapping attention to extract large context features. Extensive experiments demonstrate that GM-FlowNet outperforms RAFT, the most popular optimizationonly method, by a large margin and achieves state-ofthe-art performance on standard benchmarks. Thanks to the matching and overlapping attention, GMFlowNet obtains major improvements on the predictions for textureless regions and large motions. Our code is made publicly available at https://github.com/xiaofeng94/ GMFlowNet.

For agents

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

get_harvested_code_for_paper("2203.11335")
get_code_for_paper("2203.11335")
have("2203.11335")

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

curl https://syntology.ai/api/ran/2203.11335.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.11335.svg)](https://syntology.ai/paper/2203.11335)

Connect an agent — have() is free.