SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.08880 · IJCAI · 2023

A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement

Chi-Man Pun, Zinuo Li, Xuhang Chen, Shuqiang Wang

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 2 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/2301.08880.json · badge: /api/ran/2301.08880.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
CXH-Research/FilmNet community
Papers with Code archive
7 ran · 4 no recorded run
FunctionStatusWhere it lives
Classifier Ran
ran on a synthesized input
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("76fad11374ea4b1a")
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

def discriminator_block(in_filters, out_filters, normalization=False):
    layers = [nn.Conv2d(in_filters, out_filters, 3, stride=2, padding=1), nn.LeakyReLU(0.2)]
    if normalization:
        layers.append(nn.InstanceNorm2d(out_filters, affine=True))
    return layers

class Classifier(nn.Module):

    def __init__(self, in_channels=3, num_class=3):
        super(Classifier, self).__init__()
        self.model = nn.Sequential(nn.Upsample(size=(256, 256), mode='bilinear'), nn.Conv2d(in_channels, 16, 3, stride=2, padding=1), nn.LeakyReLU(0.2), nn.InstanceNorm2d(16, affine=True), *discriminator_block(16, 32, normalization=True), *discriminator_block(32, 64, normalization=True), *discriminator_block(64, 128, normalization=True), *discriminator_block(128, 128), nn.Dropout(p=0.5), nn.Conv2d(128, num_class, 8, padding=0))

    def forward(self, img_input):
        return self.model(img_input)

INIT_ARGS = {
    'in_channels': 3,
    'num_class': 5
}

ARGS = {
    'img_input': 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)
LFNet Ran
ran on a synthesized input
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("a22934d1d407edcd")
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 scipy import ndimage

INIT_ARGS = {
    'img_channel': 3,
    'width': 4,
    'middle_blk_num': 2,
    'enc_blk_nums': [1, 1],
    'dec_blk_nums': [1, 1]
}

# Create input tensor matching INIT_ARGS dimensions
B, C, H, W = 2, INIT_ARGS['img_channel'], 8, 8
input_tensor = torch.randn(B, C, H, W)

ARGS = {
    'inp': input_tensor
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, scipy, 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)
LUT3D Ran
ran on a synthesized input
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("f6c76a285c482463")
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, 3, 4, 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
import torch.nn.functional as F

def trilinear(img, lut):
    img = (img - 0.5) * 2.0
    lut = lut[None]
    if img.shape[0] != 1:
        lut = lut.expand(img.shape[0], -1, -1, -1, -1)
    img = img.permute(0, 2, 3, 1)[:, None]
    result = F.grid_sample(lut, img, mode='bilinear', padding_mode='border', align_corners=True)
    return result.squeeze(2)

class LUT3D(nn.Module):

    def __init__(self, dim=33, mode='zero'):
        super(LUT3D, self).__init__()
        if mode == 'zero':
            self.LUT = torch.zeros(3, dim, dim, dim, dtype=torch.float)
            self.LUT = nn.Parameter(self.LUT.clone().detach())
        elif mode == 'identity':
            if dim == 33:
                file = open('./IdentityLUT33.txt', 'r')
            elif dim == 64:
                file = open('./IdentityLUT64.txt', 'r')
            lut = file.readlines()
            self.LUT = torch.zeros(3, dim, dim, dim, dtype=torch.float)
            for i in range(0, dim):
                for j in range(0, dim):
                    for k in range(0, dim):
                        n = i * dim * dim + j * dim + k
                        x = lut[n].split()
                        self.LUT[0, i, j, k] = float(x[0])
                        self.LUT[1, i, j, k] = float(x[1])
                        self.LUT[2, i, j, k] = float(x[2])
            self.LUT = nn.Parameter(self.LUT.clone().detach())
        else:
            raise NotImplementedError

    def forward(self, img):
        return trilinear(img, self.LUT)


INIT_ARGS = {
    'dim': 8,
    'mode': 'zero'
}

ARGS = {
    'img': torch.rand(2, 3, 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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 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)
NSRBlock Ran
ran on a synthesized input
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("26dfac8684139704")
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, 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

# Import the classes from the provided code
import torch
import torch.nn as nn

class LayerNorm2d(nn.Module):

    def __init__(self, channels, eps=1e-06):
        super(LayerNorm2d, self).__init__()
        self.register_parameter('weight', nn.Parameter(torch.ones(channels)))
        self.register_parameter('bias', nn.Parameter(torch.zeros(channels)))
        self.eps = eps

    def forward(self, x):
        return LayerNormFunction.apply(x, self.weight, self.bias, self.eps)

class LayerNormFunction(torch.autograd.Function):

    @staticmethod
    def forward(ctx, x, weight, bias, eps):
        ctx.eps = eps
        N, C, H, W = x.size()
        mu = x.mean(1, keepdim=True)
        var = (x - mu).pow(2).mean(1, keepdim=True)
        y = (x - mu) / (var + eps).sqrt()
        ctx.save_for_backward(y, var, weight)
        y = weight.view(1, C, 1, 1) * y + bias.view(1, C, 1, 1)
        return y

    @staticmethod
    def backward(ctx, grad_output):
        eps = ctx.eps
        N, C, H, W = grad_output.size()
        y, var, weight = ctx.saved_variables
        g = grad_output * weight.view(1, C, 1, 1)
        mean_g = g.mean(dim=1, keepdim=True)
        mean_gy = (g * y).mean(dim=1, keepdim=True)
        gx = 1.0 / torch.sqrt(var + eps) * (g - y * mean_gy - mean_g)
        return (gx, (grad_output * y).sum(dim=3).sum(dim=2).sum(dim=0), grad_output.sum(dim=3).sum(dim=2).sum(dim=0), None)

class SimpleGate(nn.Module):

    def forward(self, x):
        x1, x2 = x.chunk(2, dim=1)
        return x1 * x2

class NSRBlock(nn.Module):

    def __init__(self, c, DW_Expand=2, FFN_Expand=2, drop_out_rate=0.0):
        super().__init__()
        dw_channel = c * DW_Expand
        self.conv1 = nn.Conv2d(in_channels=c, out_channels=dw_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.conv2 = nn.Conv2d(in_channels=dw_channel, out_channels=dw_channel, kernel_size=3, padding=1, stride=1, groups=dw_channel, bias=True)
        self.conv3 = nn.Conv2d(in_channels=dw_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.sca = nn.Sequential(nn.AdaptiveAvgPool2d(1), nn.Conv2d(in_channels=dw_channel // 2, out_channels=dw_channel // 2, kernel_size=1, padding=0, stride=1, groups=1, bias=True))
        self.sg = SimpleGate()
        ffn_channel = FFN_Expand * c
        self.conv4 = nn.Conv2d(in_channels=c, out_channels=ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.conv5 = nn.Conv2d(in_channels=ffn_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.norm1 = LayerNorm2d(c)
        self.norm2 = LayerNorm2d(c)
        self.dropout1 = nn.Dropout(drop_out_rate) if drop_out_rate > 0.0 else nn.Identity()
        self.dropout2 = nn.Dropout(drop_out_rate) if drop_out_rate > 0.0 else nn.Identity()
        self.beta = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
        self.gamma = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)

    def forward(self, inp):
        x = inp
        x = self.norm1(x)
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.sg(x)
        x = x * self.sca(x)
        x = self.conv3(x)
        x = self.dropout1(x)
        y = inp + x * self.beta
        x = self.conv4(self.norm2(y))
        x = self.sg(x)
        x = self.conv5(x)
        x = self.dropout2(x)
        return y + x * self.gamma

INIT_ARGS = {
    'c': 4,
    'DW_Expand': 2,
    'FFN_Expand': 2,
    'drop_out_rate': 0.0
}

ARGS = {
    'inp': torch.randn(2, 4, 3, 5)
}

if __name__ == '__main__':
    model = NSRBlock(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Input shape: {ARGS['inp'].shape}")
    print(f"Output shape: {output.shape}")
    print("NSRBlock executed successfully!")
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, 3, 5) — shape (2, 4, 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)
discriminator_block Ran
ran; our contract draft was wrong, not the code
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("6668c8f3b3a04df0")
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 list, ndim 1, 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

torch.manual_seed(0)

ARGS = {
    "in_filters": 3,
    "out_filters": 64,
    "normalization": True
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
gauss_kernel Ran
ran, honoured the contract we drafted
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("650511897d732139")
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 (3, 1, 5, 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

torch.manual_seed(0)

ARGS = {
    "channels": 3
}
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 (3, 1, 5, 5) — shape (3, 1, 5, 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: none by the harness; any seed is in the setup block
trilinear Ran
ran; our contract draft was wrong, not the code
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("03758e3b7e0b48e6")
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, 1, 4, 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

torch.manual_seed(0)

# img: tensor that will be normalized and permuted
# Shape: (batch, channels, height, width)
# Using batch=2, channels=3, height=4, width=5
img = torch.randn(2, 3, 4, 5)

# lut: lookup table tensor
# After lut[None], it becomes (1, C, D, H, W) where C, D, H, W are LUT dimensions
# The function uses it with grid_sample, which expects (N, C, D, H, W) for 3D sampling
# Using small dimensions: 1 channel, 6x7x8 spatial dimensions
lut = torch.randn(1, 6, 7, 8)

ARGS = {
    'img': img,
    'lut': lut,
}
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, 1, 4, 5) — shape (2, 1, 4, 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: none by the harness; any seed is in the setup block
FilmNet Not yet run
unverified (harvested, no recorded run)
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("8f596f83960db595")
How it ran

no invocation recorded.

LapPyramidConv Not yet run
unverified (harvested, no recorded run)
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("f691bdf303105b72")
How it ran

no invocation recorded.

TTR Not yet run
unverified (harvested, no recorded run)
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("f35c3d60f00bf72b")
How it ran

no invocation recorded.

TransHigh Not yet run
unverified (harvested, no recorded run)
CXH-Research/FilmNet/models/filmnet.py
code served (permissive licence) · get_code("baea583855ccfbb0")
How it ran

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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 10 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
gauss_kernel
brick of this paper's assembly: helper
1 other paper
1 later
2406.18079 (2024-06)
MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal

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

Film, a classic image style, is culturally significant to the whole photographic industry since it marks the birth of photography. However, film photography is time-consuming and expensive, necessitating a more efficient method for collecting film-style photographs. Numerous datasets that have emerged in the field of image enhancement so far are not film-specific. In order to facilitate film-based image stylization research, we construct FilmSet, a large-scale and high-quality film style dataset. Our dataset includes three different film types and more than 5000 in-the-wild high resolution images. Inspired by the features of Film-Set images, we propose a novel framework called FilmNet based on Laplacian Pyramid for stylizing images across frequency bands and achieving film style outcomes. Experiments reveal that the performance of our model is superior than state-ofthe-art techniques. The link of code and data is https://github.com/CXH-Research/FilmNet.

For agents

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

get_harvested_code_for_paper("2301.08880")
get_code_for_paper("2301.08880")
have("2301.08880")

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

curl https://syntology.ai/api/ran/2301.08880.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.08880.svg)](https://syntology.ai/paper/2301.08880)

Connect an agent — have() is free.