SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.13327 · 2024

Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 4 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/2403.13327.json · badge: /api/ran/2403.13327.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
spectacularai/3dgs-deblur canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
find_and_parse_directories_containing_splatting_metrics Ran
ran, honoured the contract we drafted
spectacularai/3dgs-deblur/parse_outputs.py
code served (permissive licence) · get_code("a6ca969619309751")
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 list, ndim 1, dtype family float; 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 os
import json
import tempfile
import shutil

# Create a temporary directory structure with the expected layout
temp_root = tempfile.mkdtemp()

# Create directory structure: dataset/variant/session/method/metrics.json
dataset_dir = os.path.join(temp_root, 'dataset1')
variant_dir = os.path.join(dataset_dir, 'variant1')
session_dir = os.path.join(variant_dir, 'session1')
method_dir = os.path.join(session_dir, 'splatfacto')
os.makedirs(method_dir, exist_ok=True)

# Create a metrics.json file
metrics_data = {
    'wall_clock_time_seconds': 3600.5,
    'results': {
        'psnr': 28.5,
        'ssim': 0.92,
        'lpips': 0.08
    }
}

metrics_path = os.path.join(method_dir, 'metrics.json')
with open(metrics_path, 'w') as f:
    json.dump(metrics_data, f)

# Create another valid example in a different dataset
dataset_dir2 = os.path.join(temp_root, 'dataset2')
variant_dir2 = os.path.join(dataset_dir2, 'variant2')
session_dir2 = os.path.join(variant_dir2, 'session2')
method_dir2 = os.path.join(session_dir2, 'splatfacto')
os.makedirs(method_dir2, exist_ok=True)

metrics_data2 = {
    'wall_clock_time_seconds': 7200.0,
    'results': {
        'psnr': 30.2,
        'ssim': 0.94,
        'lpips': 0.06
    }
}

metrics_path2 = os.path.join(method_dir2, 'metrics.json')
with open(metrics_path2, 'w') as f:
    json.dump(metrics_data2, f)

ARGS = {
    'root_dir': temp_root
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
get_original_length_seconds Ran
ran, honoured the contract we drafted
spectacularai/3dgs-deblur/render_video.py
code served (permissive licence) · get_code("8e4cf96a9ad903e6")
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 float, ndim 0, dtype family float, shape () 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 json
import tempfile
import os

# Create a temporary JSONL file with time data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_data.jsonl")

with open(temp_file, 'w') as f:
    json.dump({"time": 0.0}, f)
    f.write('\n')
    json.dump({"time": 5.5}, f)
    f.write('\n')
    json.dump({"time": 10.2}, f)
    f.write('\n')

ARGS = {
    "raw_input_data_jsonl": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
look_at Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
spectacularai/3dgs-deblur/render_video.py
code served (permissive licence) · get_code("5200d77644ff5c91")
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 2, dtype family float, shape (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 numpy as np

ARGS = {
    "cam_pos": np.array([1.0, 2.0, 3.0]),
    "cam_target": np.array([4.0, 5.0, 6.0]),
    "up_dir": np.array([0.0, 0.0, 1.0])
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 4) — shape (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: none by the harness; any seed is in the setup block
parse_metrics Ran
ran; our contract draft was wrong, not the code
spectacularai/3dgs-deblur/parse_outputs.py
code served (permissive licence) · get_code("1a099056a7c33b78")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with sample metrics
temp_dir = tempfile.mkdtemp()
metrics_file = os.path.join(temp_dir, "metrics.json")

sample_metrics = {
    "accuracy": 0.95,
    "loss": 0.12,
    "precision": 0.93,
    "recall": 0.97,
    "f1_score": 0.95
}

with open(metrics_file, 'w') as f:
    json.dump(sample_metrics, f)

ARGS = {
    "metrics_path": metrics_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float 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
quaternion_to_rotation_matrix Ran
ran, violated the contract we drafted
spectacularai/3dgs-deblur/process_synthetic_inputs.py
code served (permissive licence) · get_code("eb9595abec8daa1e")
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 2, dtype family float, shape (3, 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 numpy as np

# The function takes a quaternion in wxyz format (w, x, y, z components)
# and converts it to a 3x3 rotation matrix
# q_wxyz should be a numpy array or array-like with 4 elements

# Create a valid quaternion (normalized)
# Using a simple normalized quaternion: [w, x, y, z]
q_wxyz = np.array([1.0, 0.0, 0.0, 0.0])  # Identity rotation

ARGS = {
    "q_wxyz": q_wxyz
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (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
rotation_matrix_to_rotvec Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
spectacularai/3dgs-deblur/process_synthetic_inputs.py
code served (permissive licence) · get_code("4d9e90409902e684")
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 1, dtype family float, shape (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 torch
import numpy as np
from scipy.spatial.transform import Rotation

torch.manual_seed(0)

# Create a valid rotation matrix
# A rotation matrix must be 3x3, orthogonal, and have determinant 1
# Using scipy to generate a valid one
quat = np.array([0.0, 0.0, 0.7071068, 0.7071068])  # 90 degree rotation around z-axis
rot = Rotation.from_quat(quat)
R = rot.as_matrix()

ARGS = {
    "R": R
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (3,) — shape (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
process Not yet run
unverified (harvested, no recorded run)
spectacularai/3dgs-deblur/train_eval_split_by_blur_score.py
code served (permissive licence) · get_code("74f1182bfd36bf4b")
How it ran

no invocation recorded.

process Not yet run
unverified (harvested, no recorded run)
spectacularai/3dgs-deblur/combine.py
code served (permissive licence) · get_code("322128a1601d8e2a")
How it ran

no invocation recorded.

process Not yet run
unverified (harvested, no recorded run)
spectacularai/3dgs-deblur/process_synthetic_inputs.py
code served (permissive licence) · get_code("28c8bf6e0a340333")
How it ran

no invocation recorded.

process Not yet run
unverified (harvested, no recorded run)
spectacularai/3dgs-deblur/render_video.py
code served (permissive licence) · get_code("acaf0e4702f303d7")
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 10 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 10 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

High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data suffering from motion blur and rolling shutter distortion. Our approach is based on detailed modelling of the physical image formation process and utilizes velocities estimated using visual-inertial odometry (VIO). Camera poses are considered non-static during the exposure time of a single image frame and camera poses are further optimized in the reconstruction process. We formulate a differentiable rendering pipeline that leverages screen space approximation to efficiently incorporate rolling-shutter and motion blur effects into the 3DGS framework. Our results with both synthetic and real data demonstrate superior performance in mitigating camera motion over existing methods, thereby advancing 3DGS in naturalistic settings.

For agents

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

get_harvested_code_for_paper("2403.13327")
get_code_for_paper("2403.13327")
have("2403.13327")

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

curl https://syntology.ai/api/ran/2403.13327.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.13327.svg)](https://syntology.ai/paper/2403.13327)

Connect an agent — have() is free.