SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.02853 · CVPR · 2021

Region-aware Adaptive Instance Normalization for Image Harmonization

Xiao Gu, Jun Ling, Rong Xie, Li Song, Han Xue

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 1 has 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/2106.02853.json · badge: /api/ran/2106.02853.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
junleen/RainNet marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
RAIN Ran
ran on a synthesized input
junleen/RainNet/models/normalize.py
code served (permissive licence) · get_code("ba16261c100c88b0")
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, 8, 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
import torch.nn.functional as F

class RAIN(nn.Module):

    def __init__(self, dims_in, eps=1e-05):
        """Compute the instance normalization within only the background region, in which
            the mean and standard variance are measured from the features in background region.
        """
        super(RAIN, self).__init__()
        self.foreground_gamma = nn.Parameter(torch.zeros(dims_in), requires_grad=True)
        self.foreground_beta = nn.Parameter(torch.zeros(dims_in), requires_grad=True)
        self.background_gamma = nn.Parameter(torch.zeros(dims_in), requires_grad=True)
        self.background_beta = nn.Parameter(torch.zeros(dims_in), requires_grad=True)
        self.eps = eps

    def forward(self, x, mask):
        mask = F.interpolate(mask.detach(), size=x.size()[2:], mode='nearest')
        mean_back, std_back = self.get_foreground_mean_std(x * (1 - mask), 1 - mask)
        normalized = (x - mean_back) / std_back
        normalized_background = (normalized * (1 + self.background_gamma[None, :, None, None]) + self.background_beta[None, :, None, None]) * (1 - mask)
        mean_fore, std_fore = self.get_foreground_mean_std(x * mask, mask)
        normalized = (x - mean_fore) / std_fore * std_back + mean_back
        normalized_foreground = (normalized * (1 + self.foreground_gamma[None, :, None, None]) + self.foreground_beta[None, :, None, None]) * mask
        return normalized_foreground + normalized_background

    def get_foreground_mean_std(self, region, mask):
        sum = torch.sum(region, dim=[2, 3])
        num = torch.sum(mask, dim=[2, 3])
        mu = sum / (num + self.eps)
        mean = mu[:, :, None, None]
        var = torch.sum((region + (1 - mask) * mean - mean) ** 2, dim=[2, 3]) / (num + self.eps)
        var = var[:, :, None, None]
        return (mean, torch.sqrt(var + self.eps))


INIT_ARGS = {
    'dims_in': 4,
    'eps': 1e-05
}

ARGS = {
    'x': torch.randn(2, 4, 8, 6),
    'mask': torch.randint(0, 2, (2, 1, 4, 3), dtype=torch.float32)
}

if __name__ == '__main__':
    model = RAIN(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output dtype: {output.dtype}")
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, 8, 6) — shape (2, 4, 8, 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)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Image composition plays a common but important role in photo editing. To acquire photo-realistic composite images, one must adjust the appearance and visual style of the foreground to be compatible with the background. Existing deep learning methods for harmonizing composite images directly learn an image mapping network from the composite to real one, without explicit exploration on visual style consistency between the background and the foreground images. To ensure the visual style consistency between the foreground and the background, in this paper, we treat image harmonization as a style transfer problem. In particular, we propose a simple yet effective Region-aware Adaptive Instance Normalization (RAIN) module, which explicitly formulates the visual style from the background and adaptively applies them to the foreground. With our settings, our RAIN module can be used as a drop-in module for existing image harmonization networks and is able to bring significant improvements. Extensive experiments on the existing image harmonization benchmark datasets shows the superior capability of the proposed method. Code is available at https://github.com/junleen/RainNet.

For agents

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

get_harvested_code_for_paper("2106.02853")
get_code_for_paper("2106.02853")
have("2106.02853")

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

curl https://syntology.ai/api/ran/2106.02853.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.02853.svg)](https://syntology.ai/paper/2106.02853)

Connect an agent — have() is free.