SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.14816 · 2024

Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 7 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/2407.14816.json · badge: /api/ran/2407.14816.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
jtaoz/gkpile-deconvolution canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
act Ran
ran; our contract draft was wrong, not the code
jtaoz/gkpile-deconvolution/networks/common.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from dniku/perceptual-gradient-networks, is pointer only (licence: MPL-2.0) · get_code("e3edcd371d85dd22")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from dniku/perceptual-gradient-networks, and MPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

bn Ran
ran; our contract draft was wrong, not the code
jtaoz/gkpile-deconvolution/networks/common.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from dniku/perceptual-gradient-networks, is pointer only (licence: MPL-2.0) · get_code("cd7e7024386fb823")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from dniku/perceptual-gradient-networks, and MPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

conv Ran
ran; our contract draft was wrong, not the code
jtaoz/gkpile-deconvolution/networks/common.py
pointer only (licence: BSD-2-Clause); the stored copy get_code serves, from dniku/perceptual-gradient-networks, is pointer only (licence: MPL-2.0) · get_code("040cc21cdcd6aae9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-2-Clause), but get_code serves the stored copy, first harvested from dniku/perceptual-gradient-networks, and MPL-2.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

create_window Ran
ran, honoured the contract we drafted
jtaoz/gkpile-deconvolution/SSIM.py
code served (permissive licence) · get_code("6154e3744ece5728")
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 (3, 1, 5, 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 torch
from torch.autograd import Variable
from math import exp

torch.manual_seed(0)

def gaussian(window_size, sigma):
    gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
    return gauss / gauss.sum()

def create_window(window_size, channel):
    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
    window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
    return window

ARGS = {
    "window_size": 5,
    "channel": 3
}
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 4, dtype family float, shape (3, 1, 5, 5) — shape (3, 1, 5, 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
crop_image Ran
ran; our contract draft was wrong, not the code
jtaoz/gkpile-deconvolution/utils/common_utils.py
code served (permissive licence) · get_code("fc5ecca14cb070cc")
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 float, shape (32, 0, 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

torch.manual_seed(0)

# Create a small test image with shape (height, width, channels)
# Using 37x29x3 to ensure it's not already divisible by 32
img = np.random.rand(37, 29, 3).astype(np.float32)

ARGS = {
    "img": img,
    "d": 32
}
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 ndarray, ndim 3, dtype family float, shape (32, 0, 3) — shape (32, 0, 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
gaussian Ran
ran, honoured the contract we drafted
jtaoz/gkpile-deconvolution/SSIM.py
code served (permissive licence) · get_code("c56b7ef16f309a45")
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 Tensor, ndim 1, dtype family float, shape (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 torch
from math import exp

torch.manual_seed(0)

ARGS = {
    "window_size": 5,
    "sigma": 1.0,
}
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 Tensor, ndim 1, dtype family float, shape (5,) — shape (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
get_image_grid Ran
ran, violated the contract we drafted
jtaoz/gkpile-deconvolution/utils/common_utils.py
code served (permissive licence) · get_code("f4e1e2fda45f9f68")
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 float, shape (3, 8, 16) 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)

# Create a list of small numpy arrays representing images
# Images should be in format (C, H, W) for torchvision.utils.make_grid
# Using distinct sizes: 3 channels, 4 height, 5 width
images_np = [
    np.random.rand(3, 4, 5).astype(np.float32),
    np.random.rand(3, 4, 5).astype(np.float32),
]

ARGS = {
    "images_np": images_np,
    "nrow": 8,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — 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 float, shape (3, 8, 16) — shape (3, 8, 16) 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
get_kernel Ran
ran, honoured the contract we drafted
jtaoz/gkpile-deconvolution/networks/downsampler.py
code served (permissive licence) · get_code("7aa5f3eab66d010a")
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 (5, 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

ARGS = {
    'factor': 2,
    'kernel_type': 'lanczos',
    'phase': 0.0,
    'kernel_width': 5,
    'support': 2,
    'sigma': None,
}
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 (5, 5) — shape (5, 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
get_params Ran
ran; our contract draft was wrong, not the code
jtaoz/gkpile-deconvolution/utils/common_utils.py
code served (permissive licence) · get_code("9625c9dff59db88e")
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. 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)

# Create a simple network
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a simple downsampler
class SimpleDownsampler(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 2)
    
    def forward(self, x):
        return self.linear(x)

# Construct the arguments
net = SimpleNet()
net_input = torch.randn(2, 4)
downsampler = SimpleDownsampler()
opt_over = "net,input,down"

ARGS = {
    "opt_over": opt_over,
    "net": net,
    "net_input": net_input,
    "downsampler": downsampler
}
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 list — a list 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
random_crop_patch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jtaoz/gkpile-deconvolution/DataSets.py
code served (permissive licence) · get_code("a085c27004fdc6d1")
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 (32, 32, 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 cv2
import random
import numpy as np

random.seed(0)

# Create a sample image as a numpy array
# The function expects im to have .shape attribute and support indexing
# It uses cv2.resize, so it should be in format that cv2 understands
im = np.random.randint(0, 256, size=(64, 48, 3), dtype=np.uint8)

patch_size = 32

ARGS = {
    "im": im,
    "patch_size": patch_size
}
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 (32, 32, 3) — shape (32, 32, 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
ssim Ran
ran; our contract draft was wrong, not the code
jtaoz/gkpile-deconvolution/SSIM.py
code served (permissive licence) · get_code("9151c793f90473f0")
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. 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 torch.nn.functional as F
from torch.autograd import Variable
from math import exp

torch.manual_seed(0)

def gaussian(window_size, sigma):
    gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
    return gauss / gauss.sum()

def create_window(window_size, channel):
    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
    window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
    return window

def _ssim(img1, img2, window, window_size, channel, size_average=True):
    mu1 = F.conv2d(img1, window, padding=window_size // 2, groups=channel)
    mu2 = F.conv2d(img2, window, padding=window_size // 2, groups=channel)
    mu1_sq = mu1.pow(2)
    mu2_sq = mu2.pow(2)
    mu1_mu2 = mu1 * mu2
    sigma1_sq = F.conv2d(img1 * img1, window, padding=window_size // 2, groups=channel) - mu1_sq
    sigma2_sq = F.conv2d(img2 * img2, window, padding=window_size // 2, groups=channel) - mu2_sq
    sigma12 = F.conv2d(img1 * img2, window, padding=window_size // 2, groups=channel) - mu1_mu2
    C1 = 0.01 ** 2
    C2 = 0.03 ** 2
    ssim_map = (2 * mu1_mu2 + C1) * (2 * sigma12 + C2) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
    if size_average:
        return ssim_map.mean()
    else:
        return ssim_map.mean(1).mean(1).mean(1)

def ssim(img1, img2, window_size=11, size_average=True):
    _, channel, _, _ = img1.size()
    window = create_window(window_size, channel)
    if img1.is_cuda:
        window = window.cuda(img1.get_device())
    window = window.type_as(img1)
    return _ssim(img1, img2, window, window_size, channel, size_average)

# Create test tensors with shape [batch=2, channels=3, height=4, width=5]
img1 = torch.randn(2, 3, 4, 5)
img2 = torch.randn(2, 3, 4, 5)

ARGS = {
    "img1": img1,
    "img2": img2,
    "window_size": 11,
    "size_average": True
}
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 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
skip Not yet run
unverified (harvested, no recorded run)
jtaoz/gkpile-deconvolution/networks/skip.py
code served (permissive licence) · get_code("7237a78c59f54b81")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 3 the same month, 4 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
gaussian 160 other papers
109 dated earlier, 5 the same month, 45 later, 1 same year, order not determinable · 7 only as an assembly brick
1812.11941 (2018-12)
High Quality Monocular Depth Estimation via Transfer Learning
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
and 157 more not named here
create_window 52 other papers
42 dated earlier, 1 the same month, 9 later · 5 only as an assembly brick
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
2002.11616 (2020-02)
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
and 49 more not named here
ssim 28 other papers
24 dated earlier, 1 the same month, 3 later
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
2002.11616 (2020-02)
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
and 25 more not named here
bn 8 other papers
7 dated earlier, 1 later
1711.10925 (2017-11)
Deep Image Prior
1901.11365 (2019-01)
Noise2Self: Blind Denoising by Self-Supervision
Zang_IntraTomo_Self-Supervised_Learning-Based_Tomography_via_Sinogram_Synthesis_and_Prediction_ICCV_2021_paper (2021 (year only))
IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction
and 5 more not named here
act 6 other papers
6 dated earlier
1711.10925 (2017-11)
Deep Image Prior
1901.11365 (2019-01)
Noise2Self: Blind Denoising by Self-Supervision
Zang_IntraTomo_Self-Supervised_Learning-Based_Tomography_via_Sinogram_Synthesis_and_Prediction_ICCV_2021_paper (2021 (year only))
IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction
and 3 more not named here
conv 6 other papers
6 dated earlier
1711.10925 (2017-11)
Deep Image Prior
1901.11365 (2019-01)
Noise2Self: Blind Denoising by Self-Supervision
and 3 more not named here
get_kernel 5 other papers
5 dated earlier
2003.13659 (2020-03)
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Zang_IntraTomo_Self-Supervised_Learning-Based_Tomography_via_Sinogram_Synthesis_and_Prediction_ICCV_2021_paper (2021 (year only))
IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction
and 2 more not named here
crop_image 1 other paper
1 dated earlier
Li_Self-Supervised_Blind_Motion_Deblurring_With_Deep_Expectation_Maximization_CVPR_2023_paper (2023 (year only))
Self-supervised Blind Motion Deblurring with Deep Expectation Maximization
get_image_grid 1 other paper
1 dated earlier
Li_Self-Supervised_Blind_Motion_Deblurring_With_Deep_Expectation_Maximization_CVPR_2023_paper (2023 (year only))
Self-supervised Blind Motion Deblurring with Deep Expectation Maximization
get_params 1 other paper
1 dated earlier
Li_Self-Supervised_Blind_Motion_Deblurring_With_Deep_Expectation_Maximization_CVPR_2023_paper (2023 (year only))
Self-supervised Blind Motion Deblurring with Deep Expectation Maximization

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

Blind image deconvolution (BID) is a classic yet challenging problem in the field of image processing. Recent advances in deep image prior (DIP) have motivated a series of DIP-based approaches, demonstrating remarkable success in BID. However, due to the high non-convexity of the inherent optimization process, these methods are notorious for their sensitivity to the initialized kernel. To alleviate this issue and further improve their performance, we propose a new framework for BID that better considers the prior modeling and the initialization for blur kernels, leveraging a deep generative model. The proposed approach pre-trains a generative adversarial network-based kernel generator that aptly characterizes the kernel priors and a kernel initializer that facilitates a well-informed initialization for the blur kernel through latent space encoding. With the pre-trained kernel generator and initializer, one can obtain a high-quality initialization of the blur kernel, and enable optimization within a compact latent kernel manifold. Such a framework results in an evident performance improvement over existing DIP-based BID methods. Extensive experiments on different datasets demonstrate the effectiveness of the proposed method.

For agents

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

get_harvested_code_for_paper("2407.14816")
get_code_for_paper("2407.14816")
have("2407.14816")

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

curl https://syntology.ai/api/ran/2407.14816.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.14816.svg)](https://syntology.ai/paper/2407.14816)

Connect an agent — have() is free.