SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.08080 · ECCV · 2022

Neural Color Operators for Sequential Image Retouching

Kun Xu, Errui Ding, Xin Li, Qi Zhang, Fu Li, Yili Wang, He, Dongliang ⋆⋆, Baidu ⋆⋆

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 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; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2207.08080.json · badge: /api/ran/2207.08080.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
amberwangyili/neurop community
Papers with Code archive
5 ran · 0 no recorded run
FunctionStatusWhere it lives
Encoder Ran
ran on a synthesized input
amberwangyili/neurop/codes_pytorch/models/networks.py
code served (permissive licence) · get_code("fac6b82242ae73d4")
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 2, 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 Encoder(nn.Module):

    def __init__(self, in_nc=3, encode_nf=32):
        super(Encoder, self).__init__()
        stride = 2
        pad = 0
        self.pad = nn.ZeroPad2d(1)
        self.conv1 = nn.Conv2d(in_nc, encode_nf, 7, stride, pad, bias=True)
        self.conv2 = nn.Conv2d(encode_nf, encode_nf, 3, stride, pad, bias=True)
        self.act = nn.ReLU(inplace=True)
        self.max = nn.AdaptiveMaxPool2d((1, 1))

    def forward(self, x):
        b, _, _, _ = x.size()
        conv1_out = self.act(self.conv1(self.pad(x)))
        conv2_out = self.act(self.conv2(self.pad(conv1_out)))
        std, mean = torch.std_mean(conv2_out, dim=[2, 3], keepdim=False)
        maxs = self.max(conv2_out).squeeze(2).squeeze(2)
        out = torch.cat([std, mean, maxs], dim=1)
        return out


INIT_ARGS = {
    'in_nc': 3,
    'encode_nf': 16,
}

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

if __name__ == '__main__':
    encoder = Encoder(**INIT_ARGS)
    output = encoder(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {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 2, 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)
NeurOP Ran
ran on a synthesized input · constructed an object; no result was computed
amberwangyili/neurop/codes_pytorch/models/networks.py
code served (permissive licence) · get_code("f97e5699efa2b692")
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, through the batch API) and returned an instance of its own class, NeurOP: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Build a minimal Renderer to use as load_path alternative
def create_dummy_renderer():
    renderer = nn.Module()
    renderer.bc_block = nn.Conv2d(3, 3, 1)
    renderer.ex_block = nn.Conv2d(3, 3, 1)
    renderer.vb_block = nn.Conv2d(3, 3, 1)
    return renderer

ARGS = {
    "in_nc": 3,
    "out_nc": 3,
    "base_nf": 64,
    "encode_nf": 32,
    "load_path": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NeurOP — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a NeurOP output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
Operator Ran
ran on a synthesized input · constructed an object; no result was computed
amberwangyili/neurop/codes_pytorch/models/networks.py
code served (permissive licence) · get_code("1f9ab97f3a843e8e")
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, through the batch API) and returned an instance of its own class, Operator: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

class Operator(nn.Module):

    def __init__(self, in_nc=3, out_nc=3, base_nf=64):
        super(Operator, self).__init__()
        self.base_nf = base_nf
        self.out_nc = out_nc
        self.encoder = nn.Conv2d(in_nc, base_nf, 1, 1)
        self.mid_conv = nn.Conv2d(base_nf, base_nf, 1, 1)
        self.decoder = nn.Conv2d(base_nf, out_nc, 1, 1)
        self.act = nn.LeakyReLU(inplace=True)

    def forward(self, x, val):
        x_code = self.encoder(x)
        y_code = x_code + val
        y_code = self.act(self.mid_conv(y_code))
        y = self.decoder(y_code)
        return y

# Create an instance of the Operator to use as a test
operator_instance = Operator(in_nc=3, out_nc=3, base_nf=64)

# Create sample tensors for forward pass
# x: (batch=2, channels=3, height=4, width=5)
x = torch.randn(2, 3, 4, 5)
# val: (batch=2, channels=64, height=4, width=5) - same shape as x_code output
val = torch.randn(2, 64, 4, 5)

ARGS = {
    'in_nc': 3,
    'out_nc': 3,
    'base_nf': 64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Operator — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Operator output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
Predictor Ran
ran on a synthesized input · constructed an object; no result was computed
amberwangyili/neurop/codes_pytorch/models/networks.py
code served (permissive licence) · get_code("d43d40d4af68cd54")
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, through the batch API) and returned an instance of its own class, Predictor: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

ARGS = {
    "fea_dim": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Predictor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Predictor output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
Renderer Ran
ran on a synthesized input
amberwangyili/neurop/codes_pytorch/models/networks.py
code served (permissive licence) · get_code("7fd811178e666075")
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

class Operator(nn.Module):

    def __init__(self, in_nc=3, out_nc=3, base_nf=64):
        super(Operator, self).__init__()
        self.base_nf = base_nf
        self.out_nc = out_nc
        self.encoder = nn.Conv2d(in_nc, base_nf, 1, 1)
        self.mid_conv = nn.Conv2d(base_nf, base_nf, 1, 1)
        self.decoder = nn.Conv2d(base_nf, out_nc, 1, 1)
        self.act = nn.LeakyReLU(inplace=True)

    def forward(self, x, val):
        x_code = self.encoder(x)
        y_code = x_code + val
        y_code = self.act(self.mid_conv(y_code))
        y = self.decoder(y_code)
        return y

class Renderer(nn.Module):

    def __init__(self, in_nc=3, out_nc=3, base_nf=64):
        super(Renderer, self).__init__()
        self.in_nc = in_nc
        self.base_nf = base_nf
        self.out_nc = out_nc
        self.ex_block = Operator(in_nc, out_nc, base_nf)
        self.bc_block = Operator(in_nc, out_nc, base_nf)
        self.vb_block = Operator(in_nc, out_nc, base_nf)

    def forward(self, x_ex, x_bc, x_vb, v_ex, v_bc, v_vb):
        rec_ex = self.ex_block(x_ex, 0)
        rec_bc = self.bc_block(x_bc, 0)
        rec_vb = self.vb_block(x_vb, 0)
        map_ex = self.ex_block(x_ex, v_ex)
        map_bc = self.bc_block(x_bc, v_bc)
        map_vb = self.vb_block(x_vb, v_vb)
        return (rec_ex, rec_bc, rec_vb, map_ex, map_bc, map_vb)

INIT_ARGS = {
    'in_nc': 3,
    'out_nc': 3,
    'base_nf': 4,
}

ARGS = {
    'x_ex': torch.randn(2, 3, 8, 8),
    'x_bc': torch.randn(2, 3, 8, 8),
    'x_vb': torch.randn(2, 3, 8, 8),
    'v_ex': torch.randn(2, 4, 8, 8),
    'v_bc': torch.randn(2, 4, 8, 8),
    'v_vb': torch.randn(2, 4, 8, 8),
}

if __name__ == '__main__':
    model = Renderer(**INIT_ARGS)
    output = model(**ARGS)
    print("Output shapes:", tuple(o.shape for o in 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 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)

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a novel image retouching method by modeling the retouching process as performing a sequence of newly introduced trainable neural color operators. The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar. To reflect the homomorphism property of color operators, we employ equivariant mapping and adopt an encoder-decoder structure which maps the non-linear color transformation to a much simpler transformation (i.e., translation) in a high dimensional space. The scalar strength of each neural color operator is predicted using CNN based strength predictors by analyzing global image statistics. Overall, our method is rather lightweight and offers flexible controls. Experiments and user studies on public datasets show that our method consistently achieves the best results compared with SOTA methods in both quantitative measures and visual qualities. Code is available at https://github.com/amberwangyili/neurop.

For agents

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

get_harvested_code_for_paper("2207.08080")
get_code_for_paper("2207.08080")
have("2207.08080")

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

curl https://syntology.ai/api/ran/2207.08080.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.08080.svg)](https://syntology.ai/paper/2207.08080)

Connect an agent — have() is free.