SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.01943 · CVPR · 2023

Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo

Jenny Schmalfuss, Andrés Bruhn, Lukas Mehl, Azin Jahedi, Yaroslava Nalivayko

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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, 1 violated it and 2 have no contract verdict; 3 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/2303.01943.json · badge: /api/ran/2303.01943.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
cv-stuttgart/sceneflow_from_blender canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
cv-stuttgart/springwebsite community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
convertdisp1_optimized Ran
ran on a synthesized input
cv-stuttgart/springwebsite/memory_optimized_evaluation.py
code served (permissive licence) · get_code("34d8568de365f84e")
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 (225500050,) 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
import gc
import psutil

# Create a small submission array for testing
# The function expects an array-like object with len() and slicing support
submission = np.random.randn(5000000).astype(np.float32)

ARGS = {
    'submission': submission
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, psutil — 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 (225500050,) — shape (225500050,) 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
disp1ToFlow Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cv-stuttgart/sceneflow_from_blender/convert.py
pointer only (licence: NONE) · get_code("4e10e2aa879c7ea4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cv-stuttgart/sceneflow_from_blender 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.

disp2ToFlow Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cv-stuttgart/sceneflow_from_blender/convert.py
pointer only (licence: NONE) · get_code("5ce210a87a802dd6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cv-stuttgart/sceneflow_from_blender 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_intrinsics Ran
ran, violated the contract we drafted
cv-stuttgart/sceneflow_from_blender/cameradata.py
pointer only (licence: NONE) · get_code("6553b7d614ca8e99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cv-stuttgart/sceneflow_from_blender 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.

matchmap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cv-stuttgart/sceneflow_from_blender/convert.py
pointer only (licence: NONE) · get_code("0823b9404edb5af9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cv-stuttgart/sceneflow_from_blender 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.

read_data_in_chunks Ran
ran on a synthesized input
cv-stuttgart/springwebsite/memory_optimized_evaluation.py
code served (permissive licence) · get_code("5a11614207cccdfe")
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 (100, 5) 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
import h5py
import tempfile
import os

# Create a temporary HDF5 file with test data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, 'test_data.h5')

# Create a small HDF5 file with flow data
with h5py.File(temp_file, 'w') as f:
    # Create a dataset with shape (100, 5) - small enough to fit in memory
    data = np.random.randn(100, 5).astype(np.float32)
    f.create_dataset('flow', data=data)

ARGS = {
    'file_path': temp_file,
    'chunk_size': 30
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy, psutil — 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 (100, 5) — shape (100, 5) 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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 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.

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

While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation methodology. Hence, we introduce Spring -a large, high-resolution, high-detail, computer-generated benchmark for scene flow, optical flow, and stereo. Based on rendered scenes from the open-source Blender movie "Spring", it provides photorealistic HD datasets with state-of-the-art visual effects and ground truth training data. Furthermore, we provide a website to upload, analyze and compare results. Using a novel evaluation methodology based on a super-resolved UHD ground truth, our Spring benchmark can assess the quality of fine structures and provides further detailed performance statistics on different image regions. Regarding the number of ground truth frames, Spring is 60× larger than the only scene flow benchmark, KITTI 2015, and 15× larger than the well-established MPI Sintel optical flow benchmark. Initial results for recent methods on our benchmark show that estimating fine details is indeed challenging, as their accuracy leaves significant room for improvement. The Spring benchmark and the corresponding datasets are available at http://spring-benchmark.org.

For agents

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

get_harvested_code_for_paper("2303.01943")
get_code_for_paper("2303.01943")
have("2303.01943")

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

curl https://syntology.ai/api/ran/2303.01943.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.01943.svg)](https://syntology.ai/paper/2303.01943)

Connect an agent — have() is free.