SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.10546 · CVPR · 2021

Invertible Denoising Network: A Light Solution for Real Noise Removal

Yang Liu, Pan Ji, Zhenyue Qin, Dongwoo Kim, Tom Gedeon, Sabrina Caldwell, Saeed Anwar

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/2104.10546.json · badge: /api/ran/2104.10546.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
Yang-Liu1082/InvDN marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
HaarDownsampling Ran
ran on a synthesized input
Yang-Liu1082/InvDN/codes/models/modules/Inv_arch.py
code served (permissive licence) · get_code("c023113866818edd")
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, 12, 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
import numpy as np

class HaarDownsampling(nn.Module):

    def __init__(self, channel_in):
        super(HaarDownsampling, self).__init__()
        self.channel_in = channel_in
        self.haar_weights = torch.ones(4, 1, 2, 2)
        self.haar_weights[1, 0, 0, 1] = -1
        self.haar_weights[1, 0, 1, 1] = -1
        self.haar_weights[2, 0, 1, 0] = -1
        self.haar_weights[2, 0, 1, 1] = -1
        self.haar_weights[3, 0, 1, 0] = -1
        self.haar_weights[3, 0, 0, 1] = -1
        self.haar_weights = torch.cat([self.haar_weights] * self.channel_in, 0)
        self.haar_weights = nn.Parameter(self.haar_weights)
        self.haar_weights.requires_grad = False

    def forward(self, x, rev=False):
        if not rev:
            self.elements = x.shape[1] * x.shape[2] * x.shape[3]
            self.last_jac = self.elements / 4 * np.log(1 / 16.0)
            out = F.conv2d(x, self.haar_weights, bias=None, stride=2, groups=self.channel_in) / 4.0
            out = out.reshape([x.shape[0], self.channel_in, 4, x.shape[2] // 2, x.shape[3] // 2])
            out = torch.transpose(out, 1, 2)
            out = out.reshape([x.shape[0], self.channel_in * 4, x.shape[2] // 2, x.shape[3] // 2])
            return out
        else:
            self.elements = x.shape[1] * x.shape[2] * x.shape[3]
            self.last_jac = self.elements / 4 * np.log(16.0)
            out = x.reshape([x.shape[0], 4, self.channel_in, x.shape[2], x.shape[3]])
            out = torch.transpose(out, 1, 2)
            out = out.reshape([x.shape[0], self.channel_in * 4, x.shape[2], x.shape[3]])
            return F.conv_transpose2d(out, self.haar_weights, bias=None, stride=2, groups=self.channel_in)

    def jacobian(self, x, rev=False):
        return self.last_jac


INIT_ARGS = {
    'channel_in': 3
}

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

if __name__ == '__main__':
    model = HaarDownsampling(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Jacobian: {model.jacobian(ARGS['x'], ARGS['rev'])}")
    
    output_rev = model(output, rev=True)
    print(f"Reverse output shape: {output_rev.shape}")
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, shape (2, 12, 4, 4) — shape (2, 12, 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)
InvBlockExp Ran
ran on a synthesized input
Yang-Liu1082/InvDN/codes/models/modules/Inv_arch.py
code served (permissive licence) · get_code("1dcb7dcbafa101a5")
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, shape (2, 6) 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 SimpleSubnet(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(SimpleSubnet, self).__init__()
        self.net = nn.Sequential(
            nn.Linear(in_channels, 8),
            nn.ReLU(),
            nn.Linear(8, out_channels)
        )
    
    def forward(self, x):
        batch_size = x.shape[0]
        x_flat = x.view(batch_size, -1)
        return self.net(x_flat).view(batch_size, -1, 1, 1) if len(x.shape) == 4 else self.net(x_flat)

def subnet_constructor(in_channels, out_channels):
    return SimpleSubnet(in_channels, out_channels)

INIT_ARGS = {
    'subnet_constructor': subnet_constructor,
    'channel_num': 6,
    'channel_split_num': 3,
    'clamp': 1.0
}

ARGS = {
    'x': torch.randn(2, 6),
    'rev': False
}
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, shape (2, 6) — shape (2, 6) 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)
InvNet Ran
ran on a synthesized input
Yang-Liu1082/InvDN/codes/models/modules/Inv_arch.py
code served (permissive licence) · get_code("2485b9243f607ae1")
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

def subnet_constructor(in_channels, out_channels):
    """Simple subnet constructor for InvBlockExp"""
    return nn.Sequential(
        nn.Conv2d(in_channels, 32, 3, padding=1),
        nn.ReLU(),
        nn.Conv2d(32, out_channels, 3, padding=1)
    )

INIT_ARGS = {
    'channel_in': 3,
    'channel_out': 3,
    'subnet_constructor': subnet_constructor,
    'block_num': [2, 2],
    'down_num': 2
}

ARGS = {
    'x': torch.randn(2, 3, 16, 16),
    'rev': False,
    'cal_jacobian': True
}
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 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 2 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
HaarDownsampling
brick of this paper's assembly: model
1 other paper
1 later
2303.02353 (2023-03)
Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

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

Invertible networks have various benefits for image denoising since they are lightweight, information-lossless, and memory-saving during back-propagation. However, applying invertible models to remove noise is challenging because the input is noisy, and the reversed output is clean, following two different distributions. We propose an invertible denoising network, InvDN, to address this challenge. To discard noise and restore the clean image, InvDN replaces the noisy latent representation with another one sampled from a prior distribution during reversion. The denoising performance of InvDN is better than all the existing competitive models, achieving a new state-of-the-art result for the SIDD dataset while enjoying less run time. Moreover, the size of InvDN is far smaller, only having 4.2% of the number of parameters compared to the most recently proposed DANet. Further, via manipulating the noisy latent representation, InvDN is also able to generate noise more similar to the original one. Our code is available at: https://github.com/Yang-Liu1082/InvDN.git.

For agents

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

get_harvested_code_for_paper("2104.10546")
get_code_for_paper("2104.10546")
have("2104.10546")

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

curl https://syntology.ai/api/ran/2104.10546.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.10546.svg)](https://syntology.ai/paper/2104.10546)

Connect an agent — have() is free.