SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.03082 · 2021

Perceptual Learned Video Compression with Recurrent Conditional GAN

arXiv · PDF · Open in the Atlas

Code that ran

1 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; 1 failure of our instrument; 9 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/2109.03082.json · badge: /api/ran/2109.03082.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
RenYang-home/OpenDVC community (classifier label)
classifier basis not recorded on the link
1 ran · 9 no recorded run
FunctionStatusWhere it lives
MultiScaleSSIM Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
RenYang-home/OpenDVC/ms_ssim_np.py
code served (permissive licence) · get_code("0c7075c5c9a1bf7c")
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 float64, ndim 0, dtype family float; 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 numpy as np

# Create two sample RGB image batches
# Shape: [batch_size, height, width, channels]
batch_size = 2
height = 64
width = 64
channels = 3

# Create two distinct image arrays
img1 = np.random.randint(0, 256, (batch_size, height, width, channels), dtype=np.uint8)
img2 = np.random.randint(0, 256, (batch_size, height, width, channels), dtype=np.uint8)

# Create weights for multi-scale SSIM (5 levels as per original paper)
weights = [0.0448, 0.2856, 0.3001, 0.2363, 0.1333]

ARGS = {
    'img1': img1,
    'img2': img2,
    'max_val': 255,
    'filter_size': 11,
    'filter_sigma': 1.5,
    'k1': 0.01,
    'k2': 0.03,
    'weights': weights,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
MC Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/MC_network.py
code served (permissive licence) · get_code("cb6d3fd17b16f01e")
How it ran

no invocation recorded.

batch_normalization_layer Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/resnet.py
code served (permissive licence) · get_code("312f86edb399e5f9")
How it ran

no invocation recorded.

convnet Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/motion.py
code served (permissive licence) · get_code("35bc39682880bf95")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/load.py
code served (permissive licence) · get_code("b1b847600ecbefb7")
How it ran

no invocation recorded.

load_data_ssim Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/load.py
code served (permissive licence) · get_code("9df3dffb81dcf397")
How it ran

no invocation recorded.

loss Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/motion.py
code served (permissive licence) · get_code("fde9eefed7367d3a")
How it ran

no invocation recorded.

optical_flow Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/motion.py
code served (permissive licence) · get_code("61f9ce5dff0206b3")
How it ran

no invocation recorded.

resblock Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/MC_network.py
code served (permissive licence) · get_code("25c8754d5ef147a5")
How it ran

no invocation recorded.

tf_msssim_np Not yet run
unverified (harvested, no recorded run)
RenYang-home/OpenDVC/ms_ssim_np.py
code served (permissive licence) · get_code("2b13b01de0c26736")
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 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 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
MultiScaleSSIM 3 other papers
3 dated earlier
1611.01704 (2016-11)
End-to-end Optimized Image Compression
1811.03205 (2018-11)
Robustness of Conditional GANs to Noisy Labels
2001.01568 (2020-01)
Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
MC 1 other paper
1 dated earlier
2003.01966 (2020-03)
Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement
batch_normalization_layer 1 other paper
1 dated earlier
1603.05027 (2016-03)
Identity Mappings in Deep Residual Networks
convnet 1 other paper
1 dated earlier
2006.13560 (2020-06)
Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
loss 1 other paper
1 dated earlier
2006.13560 (2020-06)
Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
optical_flow 1 other paper
1 dated earlier
2006.13560 (2020-06)
Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
resblock 1 other paper
1 dated earlier
2003.01966 (2020-03)
Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement

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

This paper proposes a Perceptual Learned Video Compression (PLVC) approach with recurrent conditional GAN. We employ the recurrent auto-encoder-based compression network as the generator, and most importantly, we propose a recurrent conditional discriminator, which judges on raw vs. compressed video conditioned on both spatial and temporal features, including the latent representation, temporal motion and hidden states in recurrent cells. This way, the adversarial training pushes the generated video to be not only spatially photo-realistic but also temporally consistent with the groundtruth and coherent among video frames. The experimental results show that the learned PLVC model compresses video with good perceptual quality at low bit-rate, and that it outperforms the official HEVC test model (HM 16.20) and the existing learned video compression approaches for several perceptual quality metrics and user studies. The codes will be released at the project page: https://github.com/RenYang-home/PLVC.

For agents

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

get_harvested_code_for_paper("2109.03082")
get_code_for_paper("2109.03082")
have("2109.03082")

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

curl https://syntology.ai/api/ran/2109.03082.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.03082.svg)](https://syntology.ai/paper/2109.03082)

Connect an agent — have() is free.