SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.14951 · 2024

Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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, 2 violated it and 0 have no contract verdict; 5 failures of our instrument; 3 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/2404.14951.json · badge: /api/ran/2404.14951.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
yayoyo66/srstitcher canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
make_mask Ran
ran; our contract draft was wrong, not the code
yayoyo66/srstitcher/util/weighted_mask.py
code served (permissive licence) · get_code("99f9e3a213673f78")
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 tuple, ndim 3, dtype family int; 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 cv2
import numpy as np
from PIL import Image

# Create valid test masks
# mask1 and mask2 should be binary masks (uint8 arrays)
mask1 = np.zeros((64, 64), dtype=np.uint8)
mask1[10:40, 10:40] = 255

mask2 = np.zeros((64, 64), dtype=np.uint8)
mask2[30:50, 30:50] = 255

# K is the kernel size for morphological operations - must be a tuple of two odd integers
K = (5, 5)

# sigma1 and sigma2 are scaling parameters (numeric values)
sigma1 = 100
sigma2 = 50

ARGS = {
    "mask1": mask1,
    "mask2": mask2,
    "K": K,
    "sigma1": sigma1,
    "sigma2": sigma2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family int — a tuple 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
mean_pooling Ran
ran; our contract draft was wrong, not the code
yayoyo66/srstitcher/metrics/ccs.py
pointer only (licence: MIT); the stored copy get_code serves, from dengyang17/llm-proactive, is pointer only (licence: NONE) · get_code("77f69af078e09830")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dengyang17/llm-proactive, 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.

merged_img Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yayoyo66/srstitcher/util/preprocessing.py
code served (permissive licence) · get_code("bd8b93f96fe4e0a0")
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 int, shape (4, 6, 3) 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 cv2
import numpy as np

# Create sample warped images and masks for the merged_img function
# The function expects:
# - warp1, warp2: color images (3-channel uint8 arrays)
# - mask1, mask2: binary masks (single-channel uint8 arrays)

# Create small sample images
height, width = 4, 6
warp1 = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)
warp2 = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)

# Create binary masks
mask1 = np.random.randint(0, 2, (height, width), dtype=np.uint8) * 255
mask2 = np.random.randint(0, 2, (height, width), dtype=np.uint8) * 255

ARGS = {
    "warp1": warp1,
    "warp2": warp2,
    "mask1": mask1,
    "mask2": mask2,
}
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 int, shape (4, 6, 3) — shape (4, 6, 3) 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
prepare_mask_and_masked_image Ran
ran; our contract draft was wrong, not the code
yayoyo66/srstitcher/pipes/diff_pipe_inpaint.py
code served (permissive licence) · get_code("3e43cde496b041c3")
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 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 numpy as np
import torch
from PIL import Image

torch.manual_seed(0)

# Create a small PIL Image for testing (4x3 RGB)
image_array = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)
image = Image.fromarray(image_array, mode='RGB')

# Create a small PIL Image for mask (4x3 grayscale)
mask_array = np.random.randint(0, 256, size=(4, 3), dtype=np.uint8)
mask = Image.fromarray(mask_array, mode='L')

ARGS = {
    'image': image,
    'mask': mask
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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: none by the harness; any seed is in the setup block
preprocess Ran
ran, violated the contract we drafted
yayoyo66/srstitcher/pipes/diff_pipe_SD2.py
code served (permissive licence) · get_code("67094dd5e74cc749")
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 4, dtype family float, shape (1, 3, 16, 16) 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 numpy as np
import PIL
from PIL import Image

torch.manual_seed(0)

# Create a small PIL Image for testing
pil_image = Image.new('RGB', (16, 16), color=(255, 0, 0))

# Test case 1: single PIL Image
image_pil_single = pil_image

# Test case 2: list of PIL Images
image_pil_list = [pil_image, pil_image]

# Test case 3: torch tensor
image_tensor = torch.randn(2, 3, 16, 16)

# Test case 4: list of torch tensors
image_tensor_list = [torch.randn(1, 3, 16, 16), torch.randn(1, 3, 16, 16)]

ARGS = {
    "image": image_pil_single
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, diffusers, 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 (1, 3, 16, 16) — shape (1, 3, 16, 16) 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
preprocess Ran
ran, violated the contract we drafted
yayoyo66/srstitcher/pipes/diff_pipe_unclip.py
code served (permissive licence) · get_code("23ac45287b4184e8")
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 4, dtype family float, shape (1, 3, 16, 16) 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 numpy as np
import PIL.Image

torch.manual_seed(0)

# Create a test PIL Image
def create_test_pil_image():
    # Create a simple RGB image (16x16 to ensure it's divisible by 8)
    img_array = np.random.randint(0, 256, (16, 16, 3), dtype=np.uint8)
    return PIL.Image.fromarray(img_array, mode='RGB')

# Test case 1: PIL Image input
pil_image = create_test_pil_image()

ARGS = {
    "image": pil_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, diffusers, 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 (1, 3, 16, 16) — shape (1, 3, 16, 16) 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
preprocess_image Ran
ran; our contract draft was wrong, not the code
yayoyo66/srstitcher/util/preprocessing.py
code served (permissive licence) · get_code("ca5bdde262c98a1a")
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 Image. 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.

from PIL import Image
import torch

torch.manual_seed(0)

# Create a small PIL Image object
# The function calls .convert('RGB') on it, so we need a real PIL Image
image = Image.new('RGB', (8, 6), color='red')

# newsize is passed to transforms.Resize, which expects an int or sequence of ints
newsize = (4, 3)

ARGS = {
    'image': image,
    'newsize': newsize
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
prepare_mask_and_masked_image Not yet run
unverified (harvested, no recorded run)
yayoyo66/srstitcher/pipes/diff_pipe_control.py
code served (permissive licence) · get_code("639ccf4ead55737a")
How it ran

no invocation recorded.

preprocess_map Not yet run
unverified (harvested, no recorded run)
yayoyo66/srstitcher/util/preprocessing.py
code served (permissive licence) · get_code("35553cf0d5ea88e8")
How it ran

no invocation recorded.

retrieve_latents Not yet run
unverified (harvested, no recorded run)
yayoyo66/srstitcher/pipes/diff_pipe_control.py
code served (permissive licence) · get_code("8262566e1ed7239a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 2 later) and 6 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
mean_pooling 22 other papers
11 dated earlier, 3 the same month, 8 later · 1 only as an assembly brick
2206.04624 (2022-06)
Factuality Enhanced Language Models for Open-Ended Text Generation
2023.findings-emnlp.540 (2023 (year only))
Open-ended Commonsense Reasoning with Unrestricted Answer Scope
2302.05698 (2023-02)
Compositional Exemplars for In-context Learning
and 19 more not named here
retrieve_latents 19 other papers
2 dated earlier, 1 the same month, 15 later, 1 undated
2401.07519 (2024-01)
InstantID: Zero-shot Identity-Preserving Generation in Seconds
2403.14773 (2024-03)
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
2404.06666 (2024-04)
SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
and 16 more not named here
prepare_mask_and_masked_image 1 other paper
1 dated earlier
2403.01446 (2024-03)
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts

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

Deep learning-based image stitching pipelines are typically divided into three cascading stages: registration, fusion, and rectangling. Each stage requires its own network training and is tightly coupled to the others, leading to error propagation and posing significant challenges to parameter tuning and system stability. This paper proposes the Simple and Robust Stitcher (SRStitcher), which revolutionizes the image stitching pipeline by simplifying the fusion and rectangling stages into a unified inpainting model, requiring no model training or fine-tuning. We reformulate the problem definitions of the fusion and rectangling stages and demonstrate that they can be effectively integrated into an inpainting task. Furthermore, we design the weighted masks to guide the reverse process in a pre-trained largescale diffusion model, implementing this integrated inpainting task in a single inference. Through extensive experimentation, we verify the interpretability and generalization capabilities of this unified model, demonstrating that SRStitcher outperforms state-of-the-art methods in both performance and stability. Code: https://github.com/yayoyo66/SRStitcher

For agents

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

get_harvested_code_for_paper("2404.14951")
get_code_for_paper("2404.14951")
have("2404.14951")

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

curl https://syntology.ai/api/ran/2404.14951.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.14951.svg)](https://syntology.ai/paper/2404.14951)

Connect an agent — have() is free.