SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.08601 · 2024

Learning A Low-Level Vision Generalist via Visual Task Prompt

arXiv · PDF · Open in the Atlas

Code that ran

4 of 10 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, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 6 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/2408.08601.json · badge: /api/ran/2408.08601.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
chxy95/genlv canonical (classifier label)
classifier basis: census
4 ran · 6 no recorded run
FunctionStatusWhere it lives
create_3_grid_from_np_images Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chxy95/genlv/conference_version/evaluation_vit_prompt.py
code served (permissive licence) · get_code("d5ff9745fc569588")
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 (4, 9, 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 numpy as np

# Create three numpy arrays with compatible shapes for the grid function
# The function creates a canvas and places images side by side
# Shape: (height, width, channels)

height = 4
width = 3
channels = 3

# Create input image
input_img = np.random.rand(height, width, channels).astype(np.float32)

# Create prediction image (same shape as input)
pred_img = np.random.rand(height, width, channels).astype(np.float32)

# Create target image (same shape, used to determine canvas size)
target_img = np.random.rand(height, width, channels).astype(np.float32)

ARGS = {
    "input_img": input_img,
    "pred_img": pred_img,
    "target_img": target_img
}
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 3, dtype family float, shape (4, 9, 3) — shape (4, 9, 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
expand_dim Ran
ran; our contract draft was wrong, not the code
chxy95/genlv/conference_version/models_xrestormer_prompt_crossattn_wores.py
code served (permissive licence) · get_code("042da966a79899bf")
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 3, dtype family float, shape (2, 3, 4) 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)

# Create a small tensor with distinct dimensions: batch=2, features=4
t = torch.randn(2, 4)

# dim parameter: which dimension to expand
dim = 1

# k parameter: how many times to expand that dimension
k = 3

ARGS = {
    "t": t,
    "dim": dim,
    "k": k,
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 4) 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
to_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chxy95/genlv/conference_version/models_xrestormer_prompt_crossattn_wores.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("82a15cc1e46f7e4d")
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 gladzhang/Xformer, 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.

to_4d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chxy95/genlv/conference_version/models_xrestormer_prompt_crossattn_wores.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("b20f2a5df739a59e")
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 gladzhang/Xformer, 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.

add_degradation_two_images Not yet run
unverified (harvested, no recorded run)
chxy95/genlv/conference_version/dataset/genlv_dataloader.py
code served (permissive licence) · get_code("98da48cfd7d11703")
How it ran

no invocation recorded.

add_x_distortion_two_images Not yet run
unverified (harvested, no recorded run)
chxy95/genlv/conference_version/dataset/genlv_dataloader.py
code served (permissive licence) · get_code("bfb65dbbd790d987")
How it ran

no invocation recorded.

add_x_distortion_two_images Not yet run
unverified (harvested, no recorded run)
chxy95/genlv/extended_version/dataset/genlv_100_dataloader.py
code served (permissive licence) · get_code("175aa529fb1ddac4")
How it ran

no invocation recorded.

calculate_operators_two_images Not yet run
unverified (harvested, no recorded run)
chxy95/genlv/conference_version/dataset/genlv_dataloader.py
code served (permissive licence) · get_code("ab5fc8a71e547c93")
How it ran

no invocation recorded.

calculate_operators_two_images Not yet run
unverified (harvested, no recorded run)
chxy95/genlv/extended_version/dataset/genlv_100_dataloader.py
code served (permissive licence) · get_code("0330c0ccdad3ac5f")
How it ran

no invocation recorded.

create_2_grid_from_np_images Not yet run
unverified (harvested, no recorded run)
chxy95/genlv/conference_version/evaluation_vit_prompt.py
code served (permissive licence) · get_code("fc065a68df58b44a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
to_3d 80 other papers
53 dated earlier, 4 the same month, 21 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 77 more not named here
to_4d 79 other papers
52 dated earlier, 4 the same month, 21 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 76 more not named here
expand_dim 4 other papers
4 dated earlier
2101.11605 (2021-01)
Bottleneck Transformers for Visual Recognition
2103.12731 (2021-03)
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
2310.11881 (2023-10)
A Comparative Study of Image Restoration Networks for General Backbone Network Design
and 1 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Building a unified model for general low-level vision tasks holds significant research and practical value. Current methods encounter several critical issues. Multi-task restoration approaches can address multiple degradation-to-clean restoration tasks, while their applicability to tasks with different target domains (e.g., image stylization) is limited. Methods like PromptGIP can handle multiple input-target domains but rely on the Masked Autoencoder (MAE) paradigm. Consequently, they are tied to the ViT architecture, resulting in suboptimal image reconstruction quality. In addition, these methods are sensitive to prompt image content and often struggle with low-frequency information processing. In this paper, we propose a Visual task Prompt-based Image Processing (VPIP) framework to overcome these challenges. VPIP employs visual task prompts to manage tasks with different input-target domains and allows flexible selection of backbone network suitable for general tasks. Besides, a new prompt cross-attention is introduced to facilitate interaction between the input and prompt information. Based on the VPIP framework, we train a low-level vision generalist model, namely GenLV, on 30 diverse tasks. Experimental results show that GenLV can successfully address a variety of low-level tasks, significantly outperforming existing methods both quantitatively and qualitatively. Codes are available at https://github.com/chxy95/GenLV.

For agents

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

get_harvested_code_for_paper("2408.08601")
get_code_for_paper("2408.08601")
have("2408.08601")

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

curl https://syntology.ai/api/ran/2408.08601.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.08601.svg)](https://syntology.ai/paper/2408.08601)

Connect an agent — have() is free.