SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.09600 · CVPR · 2021

FVC: A New Framework towards Deep Video Compression in Feature Space

Dong Xu, Guo Lu, Zhihao Hu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 3 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/2105.09600.json · badge: /api/ran/2105.09600.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
zhihaohu/pytorchvideocompression marked official in Papers with Code
Papers with Code archive
2 ran · 3 no recorded run
FunctionStatusWhere it lives
Bitparm Ran
ran on a synthesized input · constructed an object; no result was computed
zhihaohu/pytorchvideocompression/FVC/net.py
code served (permissive licence) · get_code("ce3ca60159184ae7")
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 an instance of its own class, Bitparm: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Test case 1: non-final Bitparm
bitparm_non_final = nn.Module()
ARGS = {
    "channel": 4,
    "final": False,
}

# Verify the setup works by instantiating
model = nn.Module.__new__(type('Bitparm', (nn.Module,), {
    '__init__': lambda self, channel, final=False: None
}))

# Test case 2: final Bitparm
ARGS_FINAL = {
    "channel": 4,
    "final": True,
}

# Use the non-final case as the primary ARGS
ARGS = {
    "channel": 4,
    "final": False,
}
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 Bitparm — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Bitparm output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
ICLR17EntropyCoder Ran
ran on a synthesized input · constructed an object; no result was computed
zhihaohu/pytorchvideocompression/FVC/net.py
code served (permissive licence) · get_code("d868f1b14a374d0a")
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 an instance of its own class, ICLR17EntropyCoder: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

# Define the Q function that is used in the forward pass
def Q(x, training):
    """Quantization function - rounds to nearest integer during inference, adds noise during training"""
    if training:
        return x + torch.rand_like(x) - 0.5
    else:
        return torch.round(x)

# Create a small input tensor: batch_size=2, channels=4, height=3, width=3
x = torch.randn(2, 4, 3, 3)

# Create the entropy coder with channel=4
channel = 4

ARGS = {
    "channel": channel
}
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 ICLR17EntropyCoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ICLR17EntropyCoder output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
NIPS18nocEntropyCoder Not yet run
unverified (harvested, no recorded run)
zhihaohu/pytorchvideocompression/FVC/net.py
code served (permissive licence) · get_code("42163c1dd71addc8")
How it ran

no invocation recorded.

Parameter_net Not yet run
unverified (harvested, no recorded run)
zhihaohu/pytorchvideocompression/FVC/net.py
code served (permissive licence) · get_code("e96b231fe0b3d782")
How it ran

no invocation recorded.

VideoCompressor Not yet run
unverified (harvested, no recorded run)
zhihaohu/pytorchvideocompression/FVC/net.py
code served (permissive licence) · get_code("b901f12d4cea2635")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
Bitparm
brick of this paper's assembly: helper
1 other paper
1 later
2109.15047 (2021-09)
Deep Contextual Video Compression

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

Learning based video compression attracts increasing attention in the past few years. The previous hybrid coding approaches rely on pixel space operations to reduce spatial and temporal redundancy, which may suffer from inaccurate motion estimation or less effective motion compensation. In this work, we propose a feature-space video coding network (FVC) by performing all major operations (i.e., motion estimation, motion compression, motion compensation and residual compression) in the feature space. Specifically, in the proposed deformable compensation module, we first apply motion estimation in the feature space to produce motion information (i.e., the offset maps), which will be compressed by using the auto-encoder style network. Then we perform motion compensation by using deformable convolution and generate the predicted feature. After that, we compress the residual feature between the feature from the current frame and the predicted feature from our deformable compensation module. For better frame reconstruction, the reference features from multiple previous reconstructed frames are also fused by using the nonlocal attention mechanism in the multi-frame feature fusion module. Comprehensive experimental results demonstrate that the proposed framework achieves the state-of-the-art performance on four benchmark datasets including HEVC, UVG, VTL and MCL-JCV.

For agents

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

get_harvested_code_for_paper("2105.09600")
get_code_for_paper("2105.09600")
have("2105.09600")

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

curl https://syntology.ai/api/ran/2105.09600.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.09600.svg)](https://syntology.ai/paper/2105.09600)

Connect an agent — have() is free.