SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.21771 · CVPR · 2025

A Unified Image-Dense Annotation Generation Model for Underwater Scenes

Xiang Bai, Dingkang Liang, Hongkai Lin, Zhenghao Qi

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 3 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/2503.21771.json · badge: /api/ran/2503.21771.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
hongklin/tide canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_distance Ran
ran on a synthesized input
hongklin/tide/tide/utils/mask_process.py
code served (permissive licence) · get_code("8578046d76d864c0")
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 (2, 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 two sample matrices for compute_distance
# matrix_A: shape (2, 4) - 2 points in 4D space
matrix_A = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
], dtype=np.float32)

# matrix_B: shape (3, 4) - 3 points in 4D space
matrix_B = np.array([
    [1.5, 2.5, 3.5, 4.5],
    [5.5, 6.5, 7.5, 8.5],
    [0.5, 1.5, 2.5, 3.5]
], dtype=np.float32)

ARGS = {
    "matrix_A": matrix_A,
    "matrix_B": matrix_B
}
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 (2, 3) — shape (2, 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
get_closest_hw Ran
ran on a synthesized input
hongklin/tide/tide/pipeline/pipeline_tide.py
code served (permissive licence) · get_code("91f48b8ef03af0b7")
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, ndim 1, dtype family int; 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 numpy as np
from PIL import Image

# The function get_closest_hw takes:
# - width: int
# - height: int
# - image_size: int

# Create simple test values
ARGS = {
    "width": 800,
    "height": 600,
    "image_size": 1024
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, diffusers, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
pyramid_noise_like Ran
ran on a synthesized input
hongklin/tide/tide/train_tide_hf.py
code served (permissive licence) · get_code("4fc8ace7c32527c0")
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 (2, 4, 8, 6) 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 random

torch.manual_seed(0)

# The function expects:
# - x: a tensor with shape (b, c, w, h) - batch, channels, width, height
# - discount: a float parameter (default 0.9)

# Create a small tensor with distinct dimensions for probing
# batch=2, channels=4, width=8, height=6
x = torch.randn(2, 4, 8, 6)

ARGS = {
    "x": x,
    "discount": 0.9
}
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 (2, 4, 8, 6) — shape (2, 4, 8, 6) 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
retrieve_timesteps Ran
ran; our contract draft was wrong, not the code
hongklin/tide/tide/pipeline/pipeline_tide.py
code served (permissive licence) · get_code("5e49900a73989947")
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 inspect
from typing import List, Optional, Union

# Create a minimal scheduler mock that satisfies the function's requirements
class MinimalScheduler:
    def __init__(self, supports_timesteps=True, supports_sigmas=False):
        self.supports_timesteps = supports_timesteps
        self.supports_sigmas = supports_sigmas
        self.timesteps = torch.tensor([999, 500, 250, 0], dtype=torch.long)
    
    def set_timesteps(self, num_inference_steps: Optional[int] = None, 
                      device: Optional[Union[str, torch.device]] = None,
                      timesteps: Optional[List[int]] = None,
                      sigmas: Optional[List[float]] = None,
                      **kwargs):
        """Mock set_timesteps that handles custom timesteps and sigmas"""
        if timesteps is not None:
            self.timesteps = torch.tensor(timesteps, dtype=torch.long)
        elif sigmas is not None:
            # Convert sigmas to timesteps (mock implementation)
            self.timesteps = torch.tensor([int(999 * (1 - s)) for s in sigmas], dtype=torch.long)
        else:
            # Use num_inference_steps
            self.timesteps = torch.linspace(999, 0, num_inference_steps or 4, dtype=torch.long)
        
        if device is not None:
            self.timesteps = self.timesteps.to(device)

torch.manual_seed(0)

# Create scheduler that accepts timesteps
scheduler = MinimalScheduler(supports_timesteps=True, supports_sigmas=False)

# Define arguments for the function
ARGS = {
    'scheduler': scheduler,
    'num_inference_steps': 4,
    'device': 'cpu',
    'timesteps': None,
    'sigmas': None,
}
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 3 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
retrieve_timesteps 46 other papers
19 dated earlier, 2 the same month, 22 later, 1 same year, order not determinable, 2 undated
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2402.10491 (2024-02)
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
2405.18991 (2024-05)
EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation
and 43 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

Figure 1. We present TIDE, a unified underwater image-dense annotation generation model. Its core lies in the shared layout information and the natural complementarity between multimodal features. Our model, derived from the text-to-image model and finetuned with underwater data, enables the generation of highly consistent underwater image-dense annotations from solely text conditions.

For agents

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

get_harvested_code_for_paper("2503.21771")
get_code_for_paper("2503.21771")
have("2503.21771")

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

curl https://syntology.ai/api/ran/2503.21771.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.21771.svg)](https://syntology.ai/paper/2503.21771)

Connect an agent — have() is free.