SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 01824 · ECCV · 2024

Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models

Joost Van De Weijer, Marco Buzzelli, Claudio Rota

Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/01824.json · badge: /api/ran/01824.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
claudiom4sir/StableVSR canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
claudiom4sir/StableVSR/scheduler/ddpm_scheduler.py
pointer only (licence: MIT); the stored copy get_code serves, from jabir-zheng/TCD, is pointer only (licence: NONE) · get_code("f1e3f7493aad4745")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jabir-zheng/TCD, 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.

flow_warp Ran
ran; our contract draft was wrong, not the code
claudiom4sir/StableVSR/util/flow_utils.py
code served (permissive licence) · get_code("fa678d7e26a85ac4")
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 torch.nn.functional as F

torch.manual_seed(0)

# Create a small image/feature map tensor: (N, C, H, W) = (2, 4, 8, 6)
N, C, H, W = 2, 4, 8, 6
x = torch.randn(N, C, H, W)

# Create optical flow tensor: (N, H, W, 2)
# Flow values should be small to keep warped coordinates in reasonable range
flow = torch.randn(N, H, W, 2) * 0.5

# Define arguments dictionary
ARGS = {
    'x': x,
    'flow': flow,
    'interp_mode': 'bilinear',
    'padding_mode': 'zeros'
}
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
get_flow Ran
ran; our contract draft was wrong, not the code
claudiom4sir/StableVSR/util/flow_utils.py
code served (permissive licence) · get_code("036e886ed6d52142")
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, 5, 2) 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Build a minimal optical flow model that returns a list of flows
class MinimalOFModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(6, 2, kernel_size=3, padding=1)
    
    def forward(self, target, source):
        # Concatenate target and source along channel dimension
        x = torch.cat([target, source], dim=1)
        # Return a list of flows (the function uses flows[-1])
        flow1 = self.conv(x)
        flow2 = self.conv(x)
        return [flow1, flow2]

# Create tiny tensors: batch=2, channels=3, height=4, width=5
target = torch.randn(2, 3, 4, 5)
source = torch.randn(2, 3, 4, 5)

# Create the model
of_model = MinimalOFModel()

# Define ARGS dict with all parameters
ARGS = {
    'of_model': of_model,
    'target': target,
    'source': source,
    'rescale_factor': 1
}
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, 5, 2) — shape (2, 4, 5, 2) 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
warp_error Not yet run
unverified (harvested, no recorded run)
claudiom4sir/StableVSR/util/flow_utils.py
code served (permissive licence) · get_code("ba15a1815bb9dab1")
How it ran

no invocation recorded.

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, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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
betas_for_alpha_bar 14 other papers
3 dated earlier, 2 later, 9 same year, order not determinable
2303.01469 (2023-03)
Consistency Models
2311.15908 (2023-11)
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
2311.18832 (2023-11)
Exploiting Diffusion Prior for Generalizable Dense Prediction
and 11 more not named here
flow_warp 1 other paper
1 dated earlier
2311.15908 (2023-11)
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
get_flow 1 other paper
1 dated earlier
2311.15908 (2023-11)
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
warp_error 1 other paper
1 dated earlier
2311.15908 (2023-11)
Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models

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

to turn it into a VSR method. TCM uses the novel Temporal Texture Guidance, which provides it with spatially-aligned and detail-rich texture information synthesized in adjacent frames. This guides the generative process of the current frame toward high-quality and temporallyconsistent results. In addition, we introduce the novel Frame-wise Bidirectional Sampling strategy to encourage the use of information from past to future and vice-versa. This strategy improves the perceptual quality of the results and the temporal consistency across frames. We demonstrate the effectiveness of StableVSR in enhancing the perceptual quality of upscaled videos while achieving better temporal consistency compared to existing state-of-the-art methods for VSR. The project page is available at https://github.com/claudiom4sir/StableVSR.

For agents

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

get_harvested_code_for_paper("01824")
get_code_for_paper("01824")
have("01824")

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

curl https://syntology.ai/api/ran/01824.json

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

[![Syntology run record](https://syntology.ai/api/ran/01824.svg)](https://syntology.ai/paper/01824)

Connect an agent — have() is free.