SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.02541 · CVPR · 2023

Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder

Yikang Li, Yu Kong, Chiuman Ho, Xinmiao Lin

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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, 3 violated it and 8 have no contract verdict; 2 failures of our instrument; 2 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/2305.02541.json · badge: /api/ran/2305.02541.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
oppo-us-research/FA-VAE canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
FunctionStatusWhere it lives
configure_optimizer Ran
ran on a synthesized input
oppo-us-research/FA-VAE/utils.py
code served (permissive licence) · get_code("857a5f9aa43e2cf3")
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 AdamW. 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)

class SimpleGPT(nn.Module):
    def __init__(self):
        super().__init__()
        self.token_emb = nn.Embedding(10, 4)
        self.pos_emb = nn.Parameter(torch.randn(1, 5, 4))
        self.linear1 = nn.Linear(4, 8)
        self.linear2 = nn.Linear(8, 4)
        self.norm = nn.LayerNorm(4)
        self.attention = nn.MultiheadAttention(4, 2, batch_first=True)
    
    def forward(self, x):
        return x

gpt = SimpleGPT()

ARGS = {
    'gpt': gpt,
    'lr': 0.001,
    'wd': 0.01,
    'beta1': 0.9,
    'beta2': 0.95
}
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 AdamW — a AdamW output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AdamW 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
default Ran
ran, violated the contract we drafted
oppo-us-research/FA-VAE/models/gpt_ca.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
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 ThomasMrY/VCT, 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.

disabled_train Ran
ran, violated the contract we drafted
oppo-us-research/FA-VAE/models/txt_cond_transformer.py
code served (permissive licence) · get_code("4cb732f513d69dfd")
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 SimpleModel. 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

ARGS = {
    "self": model,
    "mode": True
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
eval_decorator Ran
ran; our contract draft was wrong, not the code
oppo-us-research/FA-VAE/models/gpt_ca.py
code served (permissive licence) · get_code("c16aee9490eb8729")
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 function. 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)

# Build a minimal model that has .training attribute and .eval()/.train() methods
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = MinimalModel()

# Define a simple function to decorate
def dummy_eval_fn(model, x):
    return model(x)

# The eval_decorator takes a function as its only parameter
ARGS = {
    "fn": dummy_eval_fn
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
exists Ran
ran, violated the contract we drafted
oppo-us-research/FA-VAE/models/gpt_ca.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

hinge_d_loss Ran
ran on a synthesized input
oppo-us-research/FA-VAE/losses/hinge.py
code served (permissive licence) · get_code("8e9b7f9a512aa375")
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 0, dtype family float, shape () 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 logits_real: output of discriminator on real data
# Shape: (N, 1, h, w) where N=2 (batch size), h=4, w=3
logits_real = torch.randn(2, 1, 4, 3)

# Create logits_fake: output of discriminator on fake data (from E->G->D)
# Shape: (N, 1, h, w) where N=2 (batch size), h=4, w=3
logits_fake = torch.randn(2, 1, 4, 3)

ARGS = {
    "logits_real": logits_real,
    "logits_fake": logits_fake,
}
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 0, dtype family float, shape () — shape () 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
hinge_d_loss Ran
ran on a synthesized input
oppo-us-research/FA-VAE/models/discriminator.py
code served (permissive licence) · get_code("e3931d2003beff13")
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 0, dtype family float, shape () 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 small float tensors for logits
logits_fake = torch.randn(2, 4, dtype=torch.float32)
logits_real = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "logits_fake": logits_fake,
    "logits_real": logits_real,
}
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 0, dtype family float, shape () — shape () 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
hinge_g_loss Ran
ran on a synthesized input
oppo-us-research/FA-VAE/losses/hinge.py
code served (permissive licence) · get_code("e7a8d15fe9e14a90")
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 0, dtype family float, shape () 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)

# logits_fake is a tensor of shape (N, 1, h, w)
# N = batch size, 1 = channel, h = height, w = width
logits_fake = torch.randn(2, 1, 4, 3)

ARGS = {
    "logits_fake": logits_fake,
}
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 0, dtype family float, shape () — shape () 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
l2norm Ran
ran; our contract draft was wrong, not the code
oppo-us-research/FA-VAE/models/l2_quantize.py
pointer only (licence: MIT); the stored copy get_code serves, from jy0205/LaVIT, is pointer only (licence: NOASSERTION) · get_code("eca6cdf05972a95e")
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 jy0205/LaVIT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

least_square_d_loss Ran
ran on a synthesized input
oppo-us-research/FA-VAE/models/discriminator.py
code served (permissive licence) · get_code("50984532271d504f")
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 0, dtype family float, shape () 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 fake logits tensor (batch_size=2, logits_dim=4)
logits_fake = torch.randn(2, 4, dtype=torch.float32)

# Create small real logits tensor (batch_size=2, logits_dim=4)
logits_real = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "logits_fake": logits_fake,
    "logits_real": logits_real,
}
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 0, dtype family float, shape () — shape () 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
recon_ffl_loss Ran
ran on a synthesized input
oppo-us-research/FA-VAE/losses/vqgan_losses.py
code served (permissive licence) · get_code("c4367203aea0f7c1")
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 0, dtype family float, shape () 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

torch.manual_seed(0)

class SimpleFFLLoss(nn.Module):
    """Minimal FFL loss module that accepts x_recon and x and returns a scalar loss."""
    def __init__(self):
        super().__init__()
    
    def forward(self, x_recon, x):
        # Focal Focal Loss typically computes some form of loss between reconstruction and target
        # Simple implementation: MSE loss
        return torch.mean((x_recon - x) ** 2)

# Create the FFL loss module
ffl = SimpleFFLLoss()

# Create small tensors: batch_size=2, dim=4
x = torch.randn(2, 4)
x_recon = torch.randn(2, 4)

ARGS = {
    "ffl": ffl,
    "x": x,
    "x_recon": x_recon,
}
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 0, dtype family float, shape () — shape () 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
recon_sl_gaussian_features_loss Ran
ran on a synthesized input
oppo-us-research/FA-VAE/losses/vqgan_losses.py
code served (permissive licence) · get_code("eeed9bf48de59e7b")
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 torch.nn as nn
import torchvision.transforms as T

torch.manual_seed(0)

# Create a simple loss function that takes two tensors and returns a scalar loss
class SimpleLoss(nn.Module):
    def forward(self, pred, target):
        return torch.nn.functional.mse_loss(pred, target)

ffl = SimpleLoss()

gaussian_kernel = 3
gaussian_sigma = 1.0

# Create encoder features: list of tensors with shape (batch, channels, height, width)
en_feat = [
    torch.randn(2, 4, 8, 8),
    torch.randn(2, 4, 6, 6),
    torch.randn(2, 4, 4, 4),
]

# Create decoder features: list of tensors with matching shapes
de_feat = [
    torch.randn(2, 4, 4, 4),
    torch.randn(2, 4, 6, 6),
    torch.randn(2, 4, 8, 8),
]

device = 'cpu'

ARGS = {
    'ffl': ffl,
    'gaussian_kernel': gaussian_kernel,
    'gaussian_sigma': gaussian_sigma,
    'en_feat': en_feat,
    'de_feat': de_feat,
    'device': device,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — 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
vanilla_d_loss Ran
ran on a synthesized input
oppo-us-research/FA-VAE/models/discriminator.py
code served (permissive licence) · get_code("1c3cd7aa5e8128bd")
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 0, dtype family float, shape () 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 small fake logits tensor (batch_size=2)
logits_fake = torch.randn(2, 4, dtype=torch.float32)

# Create small real logits tensor (batch_size=2)
logits_real = torch.randn(2, 4, dtype=torch.float32)

ARGS = {
    "logits_fake": logits_fake,
    "logits_real": logits_real,
}
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 0, dtype family float, shape () — shape () 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
build_model Not yet run
unverified (harvested, no recorded run)
oppo-us-research/FA-VAE/CLIP/clip/model.py
code served (permissive licence) · get_code("a6e226dbe417263a")
How it ran

no invocation recorded.

recon_ffl_features_loss Not yet run
unverified (harvested, no recorded run)
oppo-us-research/FA-VAE/losses/vqgan_losses.py
code served (permissive licence) · get_code("a369f81e1d3a417f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 5 the same month, 6 later) and 6 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
exists 486 other papers
174 dated earlier, 13 the same month, 293 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
disabled_train 173 other papers
22 dated earlier, 5 the same month, 146 later · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
default 163 other papers
82 dated earlier, 6 the same month, 73 later, 1 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
build_model 53 other papers
8 dated earlier, 1 the same month, 44 later
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2211.09552 (2022-11)
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
and 50 more not named here
l2norm 24 other papers
3 dated earlier, 1 the same month, 20 later · 6 only as an assembly brick
2212.09058 (2022-12)
BEATs: Audio Pre-Training with Acoustic Tokenizers
2303.04341 (2023-03)
Neural Vector Fields: Implicit Representation by Explicit Learning
2303.04743 (2023-03)
Vector Quantized Time Series Generation with a Bidirectional Prior Model
and 21 more not named here
eval_decorator 11 other papers
5 dated earlier, 6 later
1907.05242 (2019-07)
Large Memory Layers with Product Keys
2107.11906 (2021-07)
H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
and 8 more not named here
hinge_d_loss 1 other paper
1 dated earlier
2110.04627 (2021-10)
Vector-quantized Image Modeling with Improved VQGAN
least_square_d_loss 1 other paper
1 dated earlier
2110.04627 (2021-10)
Vector-quantized Image Modeling with Improved VQGAN
vanilla_d_loss 1 other paper
1 dated earlier
2110.04627 (2021-10)
Vector-quantized Image Modeling with Improved VQGAN

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

The popular VQ-VAE models reconstruct images through learning a discrete codebook but suffer from a significant issue in the rapid quality degradation of image reconstruction as the compression rate rises. One major reason is that a higher compression rate induces more loss of visual signals on the higher frequency spectrum which reflect the details on pixel space. In this paper, a Frequency Complement Module (FCM) architecture is proposed to capture the missing frequency information for enhancing reconstruction quality. The FCM can be easily incorporated into the VQ-VAE structure, and we refer to the new model as Frequancy Augmented VAE (FA-VAE). In addition, a Dynamic Spectrum Loss (DSL) is introduced to guide the FCMs to balance between various frequencies dynamically for optimal reconstruction. FA-VAE is further extended to the text-to-image synthesis task, and a Crossattention Autoregressive Transformer (CAT) is proposed to obtain more precise semantic attributes in texts. Extensive reconstruction experiments with different compression rates are conducted on several benchmark datasets, and the results demonstrate that the proposed FA-VAE is able to restore more faithfully the details compared to SOTA methods. CAT also shows improved generation quality with better image-text semantic alignment.

For agents

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

get_harvested_code_for_paper("2305.02541")
get_code_for_paper("2305.02541")
have("2305.02541")

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

curl https://syntology.ai/api/ran/2305.02541.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.02541.svg)](https://syntology.ai/paper/2305.02541)

Connect an agent — have() is free.