SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.00330 · CVPR · 2022

DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow

Hongya Wang, Pengfei Xiong, Jiankun Li, Jiangyu Liu, Zihua Zheng, Ni Nie, Zhi Ling

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 6 have no contract verdict; 1 failure 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/2204.00330.json · badge: /api/ran/2204.00330.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
zihuazheng/DIP community
Papers with Code archive
7 ran · 2 no recorded run
FunctionStatusWhere it lives
BasicEncoderQuarter Ran
ran on a synthesized input
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("804a5c97e9672f60")
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 torch.nn as nn

class ResidualBlock(nn.Module):

    def __init__(self, in_planes, planes, norm_fn='group', stride=1):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, padding=1, stride=stride)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1)
        self.relu = nn.ReLU(inplace=True)
        num_groups = planes // 8
        if norm_fn == 'group':
            self.norm1 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
            self.norm2 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
            self.norm3 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
        elif norm_fn == 'batch':
            self.norm1 = nn.BatchNorm2d(planes)
            self.norm2 = nn.BatchNorm2d(planes)
            self.norm3 = nn.BatchNorm2d(planes)
        elif norm_fn == 'instance':
            self.norm1 = nn.InstanceNorm2d(planes)
            self.norm2 = nn.InstanceNorm2d(planes)
            self.norm3 = nn.InstanceNorm2d(planes)
        elif norm_fn == 'none':
            self.norm1 = nn.Sequential()
            self.norm2 = nn.Sequential()
            self.norm3 = nn.Sequential()
        self.downsample = nn.Sequential(nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride), self.norm3)

    def forward(self, x):
        y = x
        y = self.relu(self.norm1(self.conv1(y)))
        y = self.relu(self.norm2(self.conv2(y)))
        if self.downsample is not None:
            x = self.downsample(x)
        return self.relu(x + y)

class BasicEncoderQuarter(nn.Module):

    def __init__(self, output_dim=128, norm_fn='batch', dropout=0.0):
        super(BasicEncoderQuarter, self).__init__()
        self.norm_fn = norm_fn
        if self.norm_fn == 'group':
            self.norm1 = nn.GroupNorm(num_groups=8, num_channels=64)
        elif self.norm_fn == 'batch':
            self.norm1 = nn.BatchNorm2d(64)
        elif self.norm_fn == 'instance':
            self.norm1 = nn.InstanceNorm2d(64)
        elif self.norm_fn == 'none':
            self.norm1 = nn.Sequential()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
        self.relu1 = nn.ReLU(inplace=True)
        self.in_planes = 64
        self.layer1 = self._make_layer(64, stride=1)
        self.layer2 = self._make_layer(96, stride=2)
        self.layer3 = self._make_layer(128, stride=1)
        self.conv2 = nn.Conv2d(128, output_dim, kernel_size=1)
        self.dropout = None
        if dropout > 0:
            self.dropout = nn.Dropout2d(p=dropout)
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, (nn.BatchNorm2d, nn.InstanceNorm2d, nn.GroupNorm)):
                if m.weight is not None:
                    nn.init.constant_(m.weight, 1)
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)

    def _make_layer(self, dim, stride=1):
        layer1 = ResidualBlock(self.in_planes, dim, self.norm_fn, stride=stride)
        layer2 = ResidualBlock(dim, dim, self.norm_fn, stride=1)
        layers = (layer1, layer2)
        self.in_planes = dim
        return nn.Sequential(*layers)

    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 = self.conv1(x)
        x = self.norm1(x)
        x = self.relu1(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.conv2(x)
        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': 32,
    'norm_fn': 'batch',
    'dropout': 0.0,
}

ARGS = {
    'x': torch.randn(2, 3, 64, 64),
}
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 — 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)
BasicMotionEncoder Ran
ran on a synthesized input
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("afb77da3dce3f16d")
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 torch.nn as nn
import torch.nn.functional as F

class BasicMotionEncoder(nn.Module):

    def __init__(self):
        super(BasicMotionEncoder, self).__init__()
        cor_planes = 25
        self.convc1 = nn.Conv2d(cor_planes, 64, 1, padding=0)
        self.convc2 = nn.Conv2d(64, 128, 3, padding=1)
        self.convf1 = nn.Conv2d(2, 64, 5, padding=2)
        self.convf2 = nn.Conv2d(64, 64, 3, padding=1)
        self.conv = nn.Conv2d(64 + 128, 128 - 2, 3, padding=1)

    def forward(self, flow, corr):
        cor = F.relu(self.convc1(corr))
        cor = F.relu(self.convc2(cor))
        flo = F.relu(self.convf1(flow))
        flo = F.relu(self.convf2(flo))
        cor_flo = torch.cat([cor, flo], dim=1)
        out = F.relu(self.conv(cor_flo))
        return torch.cat([out, flow], dim=1)


INIT_ARGS = {}

ARGS = {
    'flow': torch.randn(2, 2, 4, 3),
    'corr': torch.randn(2, 25, 4, 3),
}

if __name__ == '__main__':
    model = BasicMotionEncoder(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: (2, 128, 4, 3)")
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 — 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)
BasicUpdateBlock Ran
ran on a synthesized input
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("b10dd2198a786fb9")
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

class BasicMotionEncoder(nn.Module):

    def __init__(self):
        super(BasicMotionEncoder, self).__init__()
        cor_planes = 25
        self.convc1 = nn.Conv2d(cor_planes, 64, 1, padding=0)
        self.convc2 = nn.Conv2d(64, 128, 3, padding=1)
        self.convf1 = nn.Conv2d(2, 64, 5, padding=2)
        self.convf2 = nn.Conv2d(64, 64, 3, padding=1)
        self.conv = nn.Conv2d(64 + 128, 128 - 2, 3, padding=1)

    def forward(self, flow, corr):
        cor = F.relu(self.convc1(corr))
        cor = F.relu(self.convc2(cor))
        flo = F.relu(self.convf1(flow))
        flo = F.relu(self.convf2(flo))
        cor_flo = torch.cat([cor, flo], dim=1)
        out = F.relu(self.conv(cor_flo))
        return torch.cat([out, flow], dim=1)

class FlowHead(nn.Module):

    def __init__(self, input_dim=128, hidden_dim=256):
        super(FlowHead, self).__init__()
        self.conv1 = nn.Conv2d(input_dim, hidden_dim, 3, padding=1)
        self.conv2 = nn.Conv2d(hidden_dim, 2, 3, padding=1)
        self.relu = nn.ReLU(inplace=True)

    def forward(self, x):
        return self.conv2(self.relu(self.conv1(x)))

class SepConvGRU(nn.Module):

    def __init__(self, hidden_dim=128, input_dim=192 + 128):
        super(SepConvGRU, self).__init__()
        self.convz1 = nn.Conv2d(hidden_dim + input_dim, hidden_dim, (1, 5), padding=(0, 2))
        self.convr1 = nn.Conv2d(hidden_dim + input_dim, hidden_dim, (1, 5), padding=(0, 2))
        self.convq1 = nn.Conv2d(hidden_dim + input_dim, hidden_dim, (1, 5), padding=(0, 2))
        self.convz2 = nn.Conv2d(hidden_dim + input_dim, hidden_dim, (5, 1), padding=(2, 0))
        self.convr2 = nn.Conv2d(hidden_dim + input_dim, hidden_dim, (5, 1), padding=(2, 0))
        self.convq2 = nn.Conv2d(hidden_dim + input_dim, hidden_dim, (5, 1), padding=(2, 0))

    def forward(self, h, x):
        hx = torch.cat([h, x], dim=1)
        z = torch.sigmoid(self.convz1(hx))
        r = torch.sigmoid(self.convr1(hx))
        q = torch.tanh(self.convq1(torch.cat([r * h, x], dim=1)))
        h = (1 - z) * h + z * q
        hx = torch.cat([h, x], dim=1)
        z = torch.sigmoid(self.convz2(hx))
        r = torch.sigmoid(self.convr2(hx))
        q = torch.tanh(self.convq2(torch.cat([r * h, x], dim=1)))
        h = (1 - z) * h + z * q
        return h

class BasicUpdateBlock(nn.Module):

    def __init__(self, hidden_dim=128, input_dim=128):
        super(BasicUpdateBlock, self).__init__()
        self.encoder = BasicMotionEncoder()
        self.gru = SepConvGRU(hidden_dim=hidden_dim, input_dim=128 + hidden_dim)
        self.flow_head = FlowHead(hidden_dim, hidden_dim=256)
        self.mask = nn.Sequential(nn.Conv2d(128, 256, 3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(256, 16 * 9, 1, padding=0))

    def forward(self, net, inp, corr, flow, upsample=True):
        motion_features = self.encoder(flow, corr)
        inp = torch.cat([inp, motion_features], dim=1)
        net = self.gru(net, inp)
        delta_flow = self.flow_head(net)
        mask = 0.25 * self.mask(net)
        return (net, mask, delta_flow)


INIT_ARGS = {
    'hidden_dim': 128,
    'input_dim': 128,
}

ARGS = {
    'net': torch.randn(2, 128, 4, 3),
    'inp': torch.randn(2, 128, 4, 3),
    'corr': torch.randn(2, 25, 4, 3),
    'flow': torch.randn(2, 2, 4, 3),
    'upsample': True,
}

if __name__ == '__main__':
    model = BasicUpdateBlock(**INIT_ARGS)
    output = model(**ARGS)
    print("Output types:", type(output))
    print("Output length:", len(output))
    print("Net shape:", output[0].shape)
    print("Mask shape:", output[1].shape)
    print("Delta flow shape:", output[2].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)
PathMatch Ran
ran on a synthesized input
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("3addf7ba4062dadf")
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

# Create small feature maps for testing
N = 2  # batch size
C = 4  # channels (must be even, will be split into C//2 = 2)
H = 6  # height
W = 8  # width

# Feature maps with distinct spatial dimensions
fmap1 = torch.randn(N, C, H, W)
fmap2 = torch.randn(N, C, H, W)

INIT_ARGS = {
    'fmap1': fmap1,
    'fmap2': fmap2
}

# Flow field for the __call__ method
# Flow should have shape (N, 2, H, W) representing displacement in x and y
flow = torch.randn(N, 2, H, W) * 0.5  # Small displacements

ARGS = {
    'flow': flow,
    'is_search': True  # Test the search mode first
}
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)
ResidualBlock Ran
ran on a synthesized input
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("5aadf2cfb8d6853d")
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, 16, 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

class ResidualBlock(nn.Module):

    def __init__(self, in_planes, planes, norm_fn='group', stride=1):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, padding=1, stride=stride)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1)
        self.relu = nn.ReLU(inplace=True)
        num_groups = planes // 8
        if norm_fn == 'group':
            self.norm1 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
            self.norm2 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
            self.norm3 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
        elif norm_fn == 'batch':
            self.norm1 = nn.BatchNorm2d(planes)
            self.norm2 = nn.BatchNorm2d(planes)
            self.norm3 = nn.BatchNorm2d(planes)
        elif norm_fn == 'instance':
            self.norm1 = nn.InstanceNorm2d(planes)
            self.norm2 = nn.InstanceNorm2d(planes)
            self.norm3 = nn.InstanceNorm2d(planes)
        elif norm_fn == 'none':
            self.norm1 = nn.Sequential()
            self.norm2 = nn.Sequential()
            self.norm3 = nn.Sequential()
        self.downsample = nn.Sequential(nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride), self.norm3)

    def forward(self, x):
        y = x
        y = self.relu(self.norm1(self.conv1(y)))
        y = self.relu(self.norm2(self.conv2(y)))
        if self.downsample is not None:
            x = self.downsample(x)
        return self.relu(x + y)


INIT_ARGS = {
    'in_planes': 8,
    'planes': 16,
    'norm_fn': 'group',
    'stride': 1,
}

ARGS = {
    'x': torch.randn(2, 8, 4, 3),
}

if __name__ == '__main__':
    block = ResidualBlock(**INIT_ARGS)
    output = block(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: (2, 16, 4, 3)")
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, 16, 4, 3) — shape (2, 16, 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)
SmallMotionEncoder Ran
ran on a synthesized input
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("34cca1548a097a7a")
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, 96, 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
import torch.nn.functional as F

class SmallMotionEncoder(nn.Module):

    def __init__(self):
        super(SmallMotionEncoder, self).__init__()
        cor_planes = 5
        self.convc1 = nn.Conv2d(cor_planes * 2, 96, 1, padding=0)
        self.convf1 = nn.Conv2d(2, 64, 5, padding=2)
        self.convf2 = nn.Conv2d(64, 32, 3, padding=1)
        self.conv = nn.Conv2d(128, 96 - 2, 3, padding=1)

    def forward(self, flow, corr):
        cor = F.relu(self.convc1(corr))
        flo = F.relu(self.convf1(flow))
        flo = F.relu(self.convf2(flo))
        cor_flo = torch.cat([cor, flo], dim=1)
        out = F.relu(self.conv(cor_flo))
        return torch.cat([out, flow], dim=1)


INIT_ARGS = {}

ARGS = {
    'flow': torch.randn(2, 2, 4, 3),
    'corr': torch.randn(2, 10, 4, 3),
}

if __name__ == '__main__':
    model = SmallMotionEncoder(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: (2, 96, 4, 3)")
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, 96, 4, 3) — shape (2, 96, 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)
upflow4 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("fe76751cc3eec1cd")
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, 4, 12, 20) 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

torch.manual_seed(0)

# Create a small flow tensor
# flow is expected to be a 4D tensor (batch, channels, height, width)
# Using batch=2, channels=4, height=3, width=5 for distinct dimensions
flow = torch.randn(2, 4, 3, 5)

ARGS = {
    'flow': flow,
    'mode': 'bilinear'
}
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, 4, 12, 20) — shape (2, 4, 12, 20) 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
DIP Not yet run
unverified (harvested, no recorded run)
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("680b3b6dcba10757")
How it ran

no invocation recorded.

SmallUpdateBlock Not yet run
unverified (harvested, no recorded run)
zihuazheng/DIP/nets/dip.py
code served (permissive licence) · get_code("fcc2070648e55605")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow. However, the correlation volume computation requires a lot of memory, which makes prediction difficult on high-resolution images. In this paper, we propose a novel Patchmatch-based framework to work on high-resolution optical flow estimation. Specifically, we introduce the first end-to-end Patchmatch based deep learning optical flow. It can get high-precision results with lower memory benefiting from propagation and local search of Patchmatch. Furthermore, a new inverse propagation is proposed to decouple the complex operations of propagation, which can significantly reduce calculations in multiple iterations. At the time of submission, our method ranks 1 st on all the metrics on the popular KITTI2015 [28] benchmark , and ranks 2 nd on EPE on the Sintel [7] clean benchmark among published optical flow methods. Experiment shows our method has a strong cross-dataset generalization ability that the F1-all achieves 13.73%, reducing 21% from the best published result 17.4% on KITTI2015. What's more, our method shows a good details preserving result on the high-resolution dataset DAVIS [1] and consumes 2× less memory than RAFT [36]. Code will be available at github.com/zihuazheng/DIP

For agents

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

get_harvested_code_for_paper("2204.00330")
get_code_for_paper("2204.00330")
have("2204.00330")

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

curl https://syntology.ai/api/ran/2204.00330.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.00330.svg)](https://syntology.ai/paper/2204.00330)

Connect an agent — have() is free.