SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.15741 · ECCV · 2024

Segmentation-guided Layer-wise Image Vectorization with Gradient Fills

Bin Wang, Hui Zhang, Hengyu Zhou

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 0 have no contract verdict; 1 failure 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/2408.15741.json · badge: /api/ran/2408.15741.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
Rhacoal/SGLIVE marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_sine_theta Ran
ran; our contract draft was wrong, not the code
Rhacoal/SGLIVE/SGLIVE/xing_loss.py
code served (permissive licence) · get_code("10df26dd8a42e188")
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

torch.manual_seed(0)

# The function compute_sine_theta expects two arguments s1 and s2
# Each should be a tensor where:
# - s1[0, :] and s1[1, :] are two points (vectors)
# - s2[0, :] and s2[1, :] are two points (vectors)
# The function computes the sine of the angle between the two direction vectors

# Create two tensors of shape (2, 4) - 2 points with 4 dimensions each
s1 = torch.tensor([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
])

s2 = torch.tensor([
    [0.0, 1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0, 7.0]
])

ARGS = {
    "s1": s1,
    "s2": s2
}
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
xing_loss Ran
ran, honoured the contract we drafted
Rhacoal/SGLIVE/SGLIVE/xing_loss.py
code served (permissive licence) · get_code("cbeb35accd6e0b51")
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 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

torch.manual_seed(0)

# The function expects x_list to be a list of tensors
# Each tensor x should have shape (N, 2) where N is divisible by 3
# The function creates segments and computes losses based on sine of angles

# Create a small tensor with shape (9, 2) - 9 points in 2D space, divisible by 3
x1 = torch.randn(9, 2)

# Create another tensor with shape (6, 2) - 6 points in 2D space, divisible by 3
x2 = torch.randn(6, 2)

# x_list is a list of such tensors
x_list = [x1, x2]

# scale parameter
scale = 0.001

ARGS = {
    "x_list": x_list,
    "scale": scale
}
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 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
compute_sine_theta
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 same year, order not determinable
2206.04655 (2022-06)
Towards Layer-wise Image Vectorization
aaai_27987 (2024 (year only))
Optimize & Reduce: A Top-Down Approach for Image Vectorization

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

The widespread use of vector graphics creates a significant demand for vectorization methods. While recent learning-based techniques have shown their capability to create vector images of clear topology, filling these primitives with gradients remains a challenge. In this paper, we propose a segmentation-guided vectorization framework to convert raster images into concise vector graphics with radial gradient fills. With the guidance of an embedded gradient-aware segmentation subroutine, our approach progressively appends gradient-filled Bézier paths to the output, where primitive parameters are initiated with our newly designed initialization technique and are optimized to minimize our novel loss function. We build our method on a differentiable renderer with traditional segmentation algorithms to develop it as a model-free tool for raster-to-vector conversion. It is tested on various inputs to demonstrate its feasibility, independent of datasets, to synthesize vector graphics with improved visual quality and layer-wise topology compared to prior work.

For agents

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

get_harvested_code_for_paper("2408.15741")
get_code_for_paper("2408.15741")
have("2408.15741")

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

curl https://syntology.ai/api/ran/2408.15741.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.15741.svg)](https://syntology.ai/paper/2408.15741)

Connect an agent — have() is free.