SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.02376 · CVPR · 2021

Event-based Synthetic Aperture Imaging with a Hybrid Network

Yu Lei, Xiang Zhang, Wen Yang, Wei Liao

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 3 failures of our instrument; 2 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/2103.02376.json · badge: /api/ran/2103.02376.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
dvs-whu/E-SAI marked official in Papers with Code
Papers with Code archive
7 ran · 2 no recorded run
FunctionStatusWhere it lives
ActFun Ran
ran on a synthesized input · constructed an object; no result was computed
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("cf794d49d49f9ebe")
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 an instance of its own class, ActFun: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

lens = 0.5
thresh = 0.5

class ActFun(torch.autograd.Function):

    @staticmethod
    def forward(ctx, input):
        ctx.save_for_backward(input)
        return input.gt(thresh).float()

    @staticmethod
    def backward(ctx, grad_output):
        input, = ctx.saved_tensors
        grad_input = grad_output.clone()
        temp = abs(input - thresh) < lens
        return grad_input * temp.float()

# Create a small input tensor (batch size 2, dimension 4)
input_tensor = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "input": input_tensor
}
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 ActFun — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ActFun 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
Identity Ran
ran on a synthesized input
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("695cdd940a3e5a2e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, 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 torch
import torch.nn as nn

class Identity(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):
        return x

INIT_ARGS = {}

ARGS = {
    "x": torch.randn(2, 4)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 2, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ResnetBlock Ran
ran on a synthesized input · constructed an object; no result was computed
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("07fc7315a1cfc4c6")
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 an instance of its own class, ResnetBlock: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Define a simple normalization layer
norm_layer = nn.BatchNorm2d

# Construct arguments for ResnetBlock
ARGS = {
    'dim': 64,
    'padding_type': 'reflect',
    'norm_layer': norm_layer,
    'use_dropout': True,
    'use_bias': False
}
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 ResnetBlock — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ResnetBlock 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
ResnetGenerator Ran
ran on a synthesized input · constructed an object; no result was computed
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("147fbb3c65329aec")
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 an instance of its own class, ResnetGenerator: the run constructed the object and did not call it, so no result was computed. 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 functools

torch.manual_seed(0)

ARGS = {
    'input_nc': 3,
    'output_nc': 3,
    'ngf': 64,
    'norm_layer': nn.BatchNorm2d,
    'use_dropout': False,
    'n_blocks': 6,
    'padding_type': 'reflect'
}
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 ResnetGenerator — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ResnetGenerator 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
get_norm_layer Ran
ran; our contract draft was wrong, not the code
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("92ed6c48a593a6c5")
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 partial. 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 functools

torch.manual_seed(0)

ARGS = {
    'norm_type': 'instance'
}
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 partial — a partial output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a partial 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
init_net Ran
ran; our contract draft was wrong, not the code
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("8dae8fea47c19e0f")
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) and returned SimpleNet. 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 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
from torch.nn import init

torch.manual_seed(0)

# Create a simple network with Conv2d, Linear, and BatchNorm2d layers
class SimpleNet(nn.Module):
    def __init__(self):
        super(SimpleNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3)
        self.bn1 = nn.BatchNorm2d(16)
        self.linear1 = nn.Linear(16, 8)
        self.linear2 = nn.Linear(8, 4)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        return x

# Instantiate the network
net = SimpleNet()

# Define ARGS dictionary with all parameters for init_net
ARGS = {
    'net': net,
    'init_type': 'normal',
    'init_gain': 0.02,
    'gpu_ids': []
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleNet — a SimpleNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleNet 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
mem_update Ran
ran; our contract draft was wrong, not the code
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("fc04bbce50ccf4c9")
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

torch.manual_seed(0)

# Define the threshold and lens parameters used in ActFun
thresh = 0.5
lens = 0.5
decay = 0.75

class ActFun(torch.autograd.Function):
    @staticmethod
    def forward(ctx, input):
        ctx.save_for_backward(input)
        return input.gt(thresh).float()

    @staticmethod
    def backward(ctx, grad_output):
        input, = ctx.saved_tensors
        grad_input = grad_output.clone()
        temp = abs(input - thresh) < lens
        return grad_input * temp.float()

act_fun = ActFun.apply

# Create a small nn.Module that acts as 'ops'
# It should take x as input and return a tensor of the same shape
class SimpleOps(nn.Module):
    def __init__(self):
        super(SimpleOps, self).__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

# Set up the arguments for mem_update
ops = SimpleOps()
x = torch.randn(2, 4)  # batch size 2, dimension 4
mem = torch.randn(2, 4)  # same shape as x
spike = torch.zeros(2, 4)  # binary spike tensor

ARGS = {
    'ops': ops,
    'x': x,
    'mem': mem,
    'spike': spike
}
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 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
HybridNet Not yet run
unverified (harvested, no recorded run)
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("f9b79e9368142e86")
How it ran

no invocation recorded.

define_Res Not yet run
unverified (harvested, no recorded run)
dvs-whu/E-SAI/codes/Networks/Hybrid.py
code served (permissive licence) · get_code("3a87bf224d544149")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 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
init_net
brick of this paper's assembly: helper
14 other papers
8 dated earlier, 6 later
1406.2661 (2014-06)
Generative Adversarial Networks
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
and 11 more not named here
Identity
brick of this paper's assembly: helper
10 other papers
2 dated earlier, 1 the same month, 7 later · 8 only as an assembly brick
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1802.03268 (2018-02)
Efficient Neural Architecture Search via Parameter Sharing
2103.13253 (2021-03)
Learning Versatile Neural Architectures by Propagating Network Codes
and 7 more not named here
ResnetBlock
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later · 4 only as an assembly brick
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
2010.13773 (2020-10)
GreedyFool: Distortion-Aware Sparse Adversarial Attack
2203.12178 (2022-03)
Unifying Motion Deblurring and Frame Interpolation with Events
and 2 more not named here
ResnetGenerator
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
get_norm_layer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2203.12178 (2022-03)
Unifying Motion Deblurring and Frame Interpolation with Events

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

Synthetic aperture imaging (SAI) is able to achieve the see through effect by blurring out the off-focus foreground occlusions and reconstructing the in-focus occluded targets from multi-view images. However, very dense occlusions and extreme lighting conditions may bring significant disturbances to the SAI based on conventional frame-based cameras, leading to performance degeneration. To address these problems, we propose a novel SAI system based on the event camera which can produce asynchronous events with extremely low latency and high dynamic range. Thus, it can eliminate the interference of dense occlusions by measuring with almost continuous views, and simultaneously tackle the over/under exposure problems. To reconstruct the occluded targets, we propose a hybrid encoder-decoder network composed of spiking neural networks (SNNs) and convolutional neural networks (CNNs). In the hybrid network, the spatiotemporal information of the collected events is first encoded by SNN layers, and then transformed to the visual image of the occluded targets by a style-transfer CNN decoder. Through experiments, the proposed method shows remarkable performance in dealing with very dense occlusions and extreme lighting conditions, and high quality visual images can be reconstructed using pure event data.

For agents

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

get_harvested_code_for_paper("2103.02376")
get_code_for_paper("2103.02376")
have("2103.02376")

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

curl https://syntology.ai/api/ran/2103.02376.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.02376.svg)](https://syntology.ai/paper/2103.02376)

Connect an agent — have() is free.