SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.10897 · CVPR · 2022

Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

Feng Zheng, Jingkuan Song, Lianli Gao, Xiaosu Zhu, Heng Shen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 1 has no contract verdict; 3 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/2203.10897.json · badge: /api/ran/2203.10897.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
xiaosu-zhu/McQuic canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
build Ran
ran on a synthesized input
xiaosu-zhu/McQuic/mcquic/modules/builder.py
code served (permissive licence) · get_code("d789e18c19c20aa0")
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 Sequential. 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
from collections import OrderedDict

torch.manual_seed(0)

# Create a simple registry that maps layer names to layer constructors
class Registry:
    def __init__(self):
        self.layers = {
            'linear': nn.Linear,
            'relu': nn.ReLU,
            'conv': nn.Conv2d,
        }
    
    def get(self, key):
        return self.layers[key]

registry = Registry()

# Create a moduleSpec OrderedDict with layer specifications
moduleSpec = OrderedDict([
    ('linear', (
        (4, 8),  # args: (in_features, out_features)
        {}       # kwArgs: empty
    )),
    ('relu', (
        (),      # args: empty for ReLU
        {}       # kwArgs: empty
    )),
    ('linear', (
        (8, 3),  # args: (in_features, out_features)
        {}       # kwArgs: empty
    )),
])

ARGS = {
    'registry': registry,
    'moduleSpec': moduleSpec,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
get_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
xiaosu-zhu/McQuic/mcquic/modules/generator.py
code served (permissive licence) · get_code("c92c27c924b517e8")
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) and returned ndarray, ndim 2, dtype family float, shape (18, 8) 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

# Define ARGS dict with all parameters for get_2d_sincos_pos_embed
ARGS = {
    "embed_dim": 8,
    "grid_size": 4,
    "cls_token": True,
    "extra_tokens": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (18, 8) — shape (18, 8) 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
modulate Ran
ran; our contract draft was wrong, not the code
xiaosu-zhu/McQuic/mcquic/modules/generator.py
code served (permissive licence) · get_code("03310bba324ae4fb")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 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 small tensors for the modulate function
# x: input tensor with shape (batch_size, feature_dim)
x = torch.randn(2, 4)

# shift: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
shift = torch.randn(2)

# scale: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
scale = torch.randn(2)

ARGS = {
    "x": x,
    "shift": shift,
    "scale": scale,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (2, 4) — shape (2, 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
normalize_tensor Ran
ran; our contract draft was wrong, not the code
xiaosu-zhu/McQuic/mcquic/loss/lpips.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from zh460045050/V2L-Tokenizer, is pointer only (licence: NONE) · get_code("7257fdf155f5ef45")
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 zh460045050/V2L-Tokenizer, 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.

spatial_average Ran
ran; our contract draft was wrong, not the code
xiaosu-zhu/McQuic/mcquic/loss/lpips.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from zh460045050/V2L-Tokenizer, is pointer only (licence: NONE) · get_code("e268053216b1dd62")
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 zh460045050/V2L-Tokenizer, 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.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
xiaosu-zhu/McQuic/mcquic/modules/generator.py
code served (permissive licence) · get_code("665d8a4e8f673a4c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 5 later) and 1 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
get_2d_sincos_pos_embed_from_grid 190 other papers
4 dated earlier, 186 later · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
modulate 101 other papers
1 dated earlier, 99 later, 1 undated · 29 only as an assembly brick
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2303.14389 (2023-03)
Masked Diffusion Transformer is a Strong Image Synthesizer
and 98 more not named here
get_2d_sincos_pos_embed 69 other papers
69 later · 12 only as an assembly brick
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2303.14389 (2023-03)
Masked Diffusion Transformer is a Strong Image Synthesizer
2305.13311 (2023-05)
VDT: General-purpose Video Diffusion Transformers via Mask Modeling
and 66 more not named here
normalize_tensor 13 other papers
1 dated earlier, 1 the same month, 11 later
2112.00384 (2021-12)
Exploration into Translation-Equivariant Image Quantization
2203.16521 (2022-03)
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs
Xu_Versatile_Diffusion_Text_Images_and_Variations_All_in_One_Diffusion_ICCV_2023_paper (2023 (year only))
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
and 10 more not named here
spatial_average 9 other papers
1 dated earlier, 1 the same month, 7 later
2112.00384 (2021-12)
Exploration into Translation-Equivariant Image Quantization
2203.16521 (2022-03)
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs
Xu_Versatile_Diffusion_Text_Images_and_Variations_All_in_One_Diffusion_ICCV_2023_paper (2023 (year only))
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
and 6 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

Formally, trade-off between rate and distortion is handled well if priors and hyperpriors precisely describe latent variables. Current practices only adopt univariate priors and process each variable individually. However, we find intercorrelations and intra-correlations exist when observing latent variables in a vectorized perspective. These findings reveal visual redundancies to improve rate-distortion performance and parallel processing ability to speed up compression. This encourages us to propose a novel vectorized prior. Specifically, a multivariate Gaussian mixture is proposed with means and covariances to be estimated. Then, a novel probabilistic vector quantization is utilized to effectively approximate means, and remaining covariances are further induced to a unified mixture and solved by cascaded estimation without context models involved. Furthermore, codebooks involved in quantization are extended to multicodebooks for complexity reduction, which formulates an efficient compression procedure. Extensive experiments on benchmark datasets against state-of-the-art indicate our model has better rate-distortion performance and an impressive 3.18× compression speed up, giving us the ability to perform real-time, high-quality variational image compression in practice. Our source code is publicly available at https://github.com/xiaosu-zhu/McQuic.

For agents

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

get_harvested_code_for_paper("2203.10897")
get_code_for_paper("2203.10897")
have("2203.10897")

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

curl https://syntology.ai/api/ran/2203.10897.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.10897.svg)](https://syntology.ai/paper/2203.10897)

Connect an agent — have() is free.