SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.06378 · ECCV · 2024

Eliminating Warping Shakes for Unsupervised Online Video Stitching

Yao Zhao, Rui Ai, Chunyu Lin, Lang Nie, Kang Liao, Yun Zhang, Shuaicheng Liu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 0 have no contract verdict; 3 failures of our instrument; 1 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/2403.06378.json · badge: /api/ran/2403.06378.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
nie-lang/StabStitch community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_res18_FeatureMap Ran
ran; our contract draft was wrong, not the code
nie-lang/StabStitch/Codes/temporal_network.py
code served (permissive licence) · get_code("a31181c0faa7d34e")
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 torch
import torch.nn as nn
import torchvision.models as models

torch.manual_seed(0)

# Create a minimal ResNet18 model
resnet18_model = models.resnet18(pretrained=False)

# Verify the model has all the required attributes that the function accesses
assert hasattr(resnet18_model, 'conv1')
assert hasattr(resnet18_model, 'bn1')
assert hasattr(resnet18_model, 'relu')
assert hasattr(resnet18_model, 'maxpool')
assert hasattr(resnet18_model, 'layer1')
assert hasattr(resnet18_model, 'layer2')
assert hasattr(resnet18_model, 'layer3')

ARGS = {
    'resnet18_model': resnet18_model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — 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
tensor_DLT Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nie-lang/StabStitch/Codes/temporal_network.py
code served (permissive licence) · get_code("0d43cef2235f0f10")
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 3, dtype family float, shape (2, 3, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# Create small tensors for src_p and dst_p
# src_p shape: (bs, 4, 2) - batch size 2, 4 points with 2D coordinates
# dst_p shape: (bs, 4, 2) - batch size 2, 4 points with 2D coordinates
bs = 2
num_points = 4
coord_dim = 2

src_p = torch.randn(bs, num_points, coord_dim)
dst_p = torch.randn(bs, num_points, coord_dim)

ARGS = {
    "src_p": src_p,
    "dst_p": dst_p,
}
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 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 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
transformer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nie-lang/StabStitch/Codes/temporal_network.py
code served (permissive licence) · get_code("84f2876369417918")
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 (2, 3, 6, 7) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# U: input tensor [num_batch, num_channels, height, width]
U = torch.randn(2, 3, 4, 5)

# theta: transformation parameters [num_batch, 6] or will be reshaped to [num_batch, 3, 3]
# Initialize to identity transform
identity = np.array([[1., 0., 0.],
                     [0., 1., 0.],
                     [0., 0., 1.]])
theta = torch.from_numpy(identity).unsqueeze(0).expand(2, -1, -1).reshape(2, -1).float()

# out_size: tuple of (height, width)
out_size = (6, 7)

ARGS = {
    'U': U,
    'theta': theta,
    'out_size': out_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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, 3, 6, 7) — shape (2, 3, 6, 7) 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
TemporalNet Not yet run
unverified (harvested, no recorded run)
nie-lang/StabStitch/Codes/temporal_network.py
code served (permissive licence) · get_code("73c060e3b106bee6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 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
tensor_DLT
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2302.08207 (2023-02)
Parallax-Tolerant Unsupervised Deep Image Stitching
transformer
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2302.08207 (2023-02)
Parallax-Tolerant Unsupervised Deep Image Stitching

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

In this paper, we retarget video stitching to an emerging issue, named warping shake, when extending image stitching to video stitching. It unveils the temporal instability of warped content in nonoverlapping regions, despite image stitching having endeavored to preserve the natural structures. Therefore, in most cases, even if the input videos to be stitched are stable, the stitched video will inevitably cause undesired warping shakes and affect the visual experience. To eliminate the shakes, we propose StabStitch to simultaneously realize video stitching and video stabilization in a unified unsupervised learning framework. Starting from the camera paths in video stabilization, we first derive the expression of stitching trajectories in video stitching by elaborately integrating spatial and temporal warps. Then a warp smoothing model is presented to optimize them with a comprehensive consideration regarding content alignment, trajectory smoothness, spatial consistency, and online collaboration. To establish an evaluation benchmark and train the learning framework, we build a video stitching dataset with a rich diversity in camera motions and scenes. Compared with existing stitching solutions, StabStitch exhibits significant superiority in scene robustness and inference speed in addition to stitching and stabilization performance, contributing to a robust and real-time online video stitching system. The codes and dataset are available at https://github.com/nie-lang/StabStitch.

For agents

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

get_harvested_code_for_paper("2403.06378")
get_code_for_paper("2403.06378")
have("2403.06378")

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

curl https://syntology.ai/api/ran/2403.06378.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.06378.svg)](https://syntology.ai/paper/2403.06378)

Connect an agent — have() is free.