SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.11684 · 2023

SpikeCV: Open a Continuous Computer Vision Era

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2303.11684.json · badge: /api/ran/2303.11684.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
zyj061/spikecv canonical (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_psnr Ran
ran; our contract draft was wrong, not the code
zyj061/spikecv/SpikeCV/metrics/reconsturction.py
code served (permissive licence) · get_code("2b4a6b7700cb4268")
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 numpy as np
import math

def calculate_psnr(img1, img2, border=0):
    """
    calculate PSNR
    img1 and img2 have range [0, 255]
    (H x W) or (H x W x 3) numpy array
    From https://github.com/cszn/KAIR/blob/master/utils/utils_image.py
    """
    if not img1.shape == img2.shape:
        raise ValueError('Input images must have the same dimensions.')
    h, w = img1.shape[:2]
    img1 = img1[border:h - border, border:w - border]
    img2 = img2[border:h - border, border:w - border]
    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)
    mse = np.mean((img1 - img2) ** 2)
    if mse == 0:
        return float('inf')
    return 20 * math.log10(255.0 / math.sqrt(mse))


# Create test images with shape (H x W x 3) in range [0, 255]
np.random.seed(0)
img1 = np.random.randint(0, 256, size=(32, 48, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, size=(32, 48, 3), dtype=np.uint8)

ARGS = {
    'img1': img1,
    'img2': img2,
    'border': 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 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
calculate_ssim Ran
ran; our contract draft was wrong, not the code
zyj061/spikecv/SpikeCV/metrics/reconsturction.py
code served (permissive licence) · get_code("afd28a0d841543dc")
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. 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 numpy as np
import cv2

# Create two small test images with range [0, 255]
# Using distinct dimensions: 32x48 for clear shape differentiation
np.random.seed(0)

# Grayscale image test case (H x W)
img1_gray = np.random.randint(0, 256, size=(32, 48), dtype=np.uint8)
img2_gray = np.random.randint(0, 256, size=(32, 48), dtype=np.uint8)

# RGB image test case (H x W x 3)
img1_rgb = np.random.randint(0, 256, size=(32, 48, 3), dtype=np.uint8)
img2_rgb = np.random.randint(0, 256, size=(32, 48, 3), dtype=np.uint8)

# Single channel image test case (H x W x 1)
img1_single = np.random.randint(0, 256, size=(32, 48, 1), dtype=np.uint8)
img2_single = np.random.randint(0, 256, size=(32, 48, 1), dtype=np.uint8)

ARGS = {
    'img1': img1_rgb,
    'img2': img2_rgb,
    'border': 0
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
compute_aee Ran
ran on a synthesized input
zyj061/spikecv/SpikeCV/metrics/optical_flow.py
code served (permissive licence) · get_code("0b0e7673f1579d72")
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, 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 torch
import numpy as np

torch.manual_seed(0)

# The function expects two numpy arrays (or array-like objects) with shape (..., 2) for optical flow
# It computes the Euclidean distance along the last axis, then converts to tensor and takes mean

flow_gt = np.random.randn(2, 4, 2).astype(np.float32)  # batch=2, spatial=4, flow_dim=2
flow_pred = np.random.randn(2, 4, 2).astype(np.float32)  # same shape

ARGS = {
    "flow_gt": flow_gt,
    "flow_pred": flow_pred
}
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 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
is_video_file Ran
ran on a synthesized input
zyj061/spikecv/SpikeCV/spkData/convert_video.py
code served (permissive licence) · get_code("6dc6c3b5fc153123")
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 bool, 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 os

def is_video_file(file_path):
    video_extensions = ['.avi', '.mp4', '.mov', '.mkv']
    file_extension = os.path.splitext(file_path)[1].lower()
    return file_extension in video_extensions

ARGS = {
    'file_path': 'test_video.mp4'
}
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 bool, 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
ssim Ran
ran, honoured the contract we drafted
zyj061/spikecv/SpikeCV/metrics/reconsturction.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("ba721aeacc165234")
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 AlifAshrafee/Restoring-Without-Forgetting, 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.

video_to_spike Ran
ran on a synthesized input
zyj061/spikecv/SpikeCV/spkData/convert_video.py
code served (permissive licence) · get_code("dd7b50e57a0628e7")
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 (3, 6, 8) 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 os
import cv2
import numpy as np
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
frames_dir = os.path.join(temp_dir, 'frames')
os.makedirs(frames_dir, exist_ok=True)

# Create a few dummy image frames (small 8x6 grayscale images converted to BGR)
np.random.seed(0)
for i in range(3):
    frame = np.random.randint(0, 256, (6, 8, 3), dtype=np.uint8)
    cv2.imwrite(os.path.join(frames_dir, f'frame_{i:03d}.png'), frame)

# Create optional debug save folder
debug_dir = os.path.join(temp_dir, 'debug')
os.makedirs(debug_dir, exist_ok=True)

ARGS = {
    'sourefolder': frames_dir,
    'savefolder_debug': debug_dir,
    'threshold': 5.0,
    'init_noise': True,
    'format': 'png',
    'is_video': False
}
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 (3, 6, 8) — shape (3, 6, 8) 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
img_to_spike Not yet run
unverified (harvested, no recorded run)
zyj061/spikecv/SpikeCV/spkData/convert_img.py
code served (permissive licence) · get_code("82eddacabe2b0712")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 4 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
ssim 18 other papers
7 dated earlier, 1 the same month, 10 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
1904.03377 (2019-04)
Blind Super-Resolution With Iterative Kernel Correction
2005.05650 (2020-05)
Invertible Image Rescaling
and 15 more not named here
calculate_psnr 9 other papers
2 dated earlier, 1 the same month, 6 later
Zamir_Restormer_Efficient_Transformer_for_High-Resolution_Image_Restoration_CVPR_2022_paper (2022 (year only))
Restormer: Efficient Transformer for High-Resolution Image Restoration
2201.02973 (2022-01)
MAXIM: Multi-Axis MLP for Image Processing
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
and 6 more not named here
calculate_ssim 8 other papers
2 dated earlier, 1 the same month, 5 later
Zamir_Restormer_Efficient_Transformer_for_High-Resolution_Image_Restoration_CVPR_2022_paper (2022 (year only))
Restormer: Efficient Transformer for High-Resolution Image Restoration
2201.02973 (2022-01)
MAXIM: Multi-Axis MLP for Image Processing
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
and 5 more not named here

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

SpikeCV is a new open-source computer vision platform for the spike camera, which is a neuromorphic visual sensor that has developed rapidly in recent years. In the spike camera, each pixel position directly accumulates the light intensity and asynchronously fires spikes. The output binary spikes can reach a frequency of 40,000 Hz. As a new type of visual expression, spike sequence has high spatiotemporal completeness and preserves the continuous visual information of the external world. Taking advantage of the low latency and high dynamic range of the spike camera, many spike-based algorithms have made significant progress, such as high-quality imaging and ultra-high-speed target detection. To build up a community ecology for the spike vision to facilitate more users to take advantage of the spike camera, SpikeCV provides a variety of ultra-high-speed scene datasets, hardware interfaces, and an easy-to-use modules library. SpikeCV focuses on encapsulation for spike data, standardization for dataset interfaces, modularization for vision tasks, and real-time applications for challenging scenes. With the advent of the open-source Python ecosystem, modules of SpikeCV can be used as a Python library to fulfilled most of the numerical analysis needs of researchers. We demonstrate the efficiency of the SpikeCV on offline inference and real-time applications. The project repository address are \url{https://openi.pcl.ac.cn/Cordium/SpikeCV} and \url{https://github.com/Zyj061/SpikeCV

For agents

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

get_harvested_code_for_paper("2303.11684")
get_code_for_paper("2303.11684")
have("2303.11684")

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

curl https://syntology.ai/api/ran/2303.11684.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.11684.svg)](https://syntology.ai/paper/2303.11684)

Connect an agent — have() is free.