SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.02840 · NeurIPS · 2024

Test-Time Dynamic Image Fusion

Yi Ding, Changqing Zhang, Qinghua Hu, Bing Cao, Yinan Xia

arXiv · PDF · Open in the Atlas

Code that ran

9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 0 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/2411.02840.json · badge: /api/ran/2411.02840.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
Yinan-Xia/TTD canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
Im2Patch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yinan-Xia/TTD/dataprocessing.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from xujian000/DAF-Net, is pointer only (licence: NONE) · get_code("f33fb16d35caecfb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from xujian000/DAF-Net, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

VIFF Ran
ran, honoured the contract we drafted
Yinan-Xia/TTD/utils/Evaluator.py
code served (permissive licence) · get_code("4a72727e06412d3f")
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 float64, ndim 0, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:59:35Z. 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 numpy as np
from scipy.signal import convolve2d

# Create small test images as numpy arrays
# The function operates on 2D grayscale images
np.random.seed(0)

# Create three distinct-sized small images to be unambiguous
image_F = np.random.rand(16, 12).astype(np.float64)
image_A = np.random.rand(16, 12).astype(np.float64)
image_B = np.random.rand(16, 12).astype(np.float64)

ARGS = {
    "image_F": image_F,
    "image_A": image_A,
    "image_B": image_B,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
cc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yinan-Xia/TTD/utils/loss.py
code served (permissive licence) · get_code("e73e7709bbfcf0a2")
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 Tensor, ndim 0, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:59:35Z. 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

torch.manual_seed(0)

# Create two small image tensors with shape (N, C, H, W)
# N=2 (batch), C=3 (channels), H=4, W=5 (spatial dimensions)
img1 = torch.randn(2, 3, 4, 5, dtype=torch.float32)
img2 = torch.randn(2, 3, 4, 5, dtype=torch.float32)

ARGS = {
    'img1': img1,
    'img2': img2,
}
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 Tensor, ndim 0, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yinan-Xia/TTD/net.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from zhaozixiang1228/mmif-cddfuse, is pointer only (licence: NONE) · get_code("fe7d4321dbeef661")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from zhaozixiang1228/mmif-cddfuse, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_img_file Ran
ran; our contract draft was wrong, not the code
Yinan-Xia/TTD/dataprocessing.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from xujian000/DAF-Net, is pointer only (licence: NONE) · get_code("b4aafd32738c8371")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from xujian000/DAF-Net, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

image_read_cv2 Ran
ran, honoured the contract we drafted
Yinan-Xia/TTD/utils/Evaluator.py
code served (permissive licence) · get_code("9e43cb62b97207d2")
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 ndarray, ndim 3, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:59:35Z. 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 numpy as np
import cv2
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, 'test_image.png')

# Create a simple BGR image (3-channel, 100x100)
test_image_bgr = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
cv2.imwrite(temp_image_path, test_image_bgr)

ARGS = {
    'path': temp_image_path,
    'mode': 'RGB'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
rgb2y Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yinan-Xia/TTD/dataprocessing.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from xujian000/DAF-Net, is pointer only (licence: NONE) · get_code("6f19122cfbfddc13")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from xujian000/DAF-Net, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yinan-Xia/TTD/net.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("82a15cc1e46f7e4d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from gladzhang/Xformer, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_4d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yinan-Xia/TTD/net.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("b20f2a5df739a59e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from gladzhang/Xformer, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is 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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 3 later) and 3 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
drop_path 224 other papers
186 dated earlier, 6 the same month, 24 later, 7 same year, order not determinable, 1 undated · 38 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
and 221 more not named here
to_3d 80 other papers
60 dated earlier, 1 the same month, 17 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 77 more not named here
to_4d 79 other papers
59 dated earlier, 1 the same month, 17 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 76 more not named here
Im2Patch 5 other papers
5 dated earlier
1608.03981 (2016-08)
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
1901.09221 (2019-01)
Progressive Image Deraining Networks: A Better and Simpler Baseline
1907.03029 (2019-07)
Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
and 2 more not named here
get_img_file 1 other paper
1 dated earlier
2403.09065 (2024-03)
When Semantic Segmentation Meets Frequency Aliasing
rgb2y 1 other paper
1 dated earlier
2403.09065 (2024-03)
When Semantic Segmentation Meets Frequency Aliasing

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

The inherent challenge of image fusion lies in capturing the correlation of multisource images and comprehensively integrating effective information from different sources. Most existing techniques fail to perform dynamic image fusion while notably lacking theoretical guarantees, leading to potential deployment risks in this field. Is it possible to conduct dynamic image fusion with a clear theoretical justification? In this paper, we give our solution from a generalization perspective. We proceed to reveal the generalized form of image fusion and derive a new test-time dynamic image fusion paradigm. It provably reduces the upper bound of generalization error. Specifically, we decompose the fused image into multiple components corresponding to its source data. The decomposed components represent the effective information from the source data, thus the gap between them reflects the Relative Dominability (RD) of the uni-source data in constructing the fusion image. Theoretically, we prove that the key to reducing generalization error hinges on the negative correlation between the RD-based fusion weight and the uni-source reconstruction loss. Intuitively, RD dynamically highlights the dominant regions of each source and can be naturally converted to the corresponding fusion weight, achieving robust results. Extensive experiments and discussions with in-depth analysis on multiple benchmarks confirm our findings and superiority. Our code is available at https://github.com/Yinan-Xia/TTD.

For agents

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

get_harvested_code_for_paper("2411.02840")
get_code_for_paper("2411.02840")
have("2411.02840")

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

curl https://syntology.ai/api/ran/2411.02840.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.02840.svg)](https://syntology.ai/paper/2411.02840)

Connect an agent — have() is free.