Papers › Autoencoding beyond pixels using a learned similarity metric

Autoencoding beyond pixels using a learned similarity metric

31 Dec 2015arXiv:1512.09300archive 2025-07-28

Anders Boesen Lindbo Larsen, Søren Kaae Sønderby, Hugo Larochelle, Ole Winther

We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. Moreover, we show that the method learns an embedding in which high-level abstract visual features (e.g. wearing glasses) can be modified using simple arithmetic.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 6 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 13 samples from 6 repositories, 8 ran (6 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

28 repositories listed; official and paper-mentioned ones first.

5yearsKim/Feature-Subtraction-using-AE-GAN mentioned on GitHubpytorchSyntology: not harvested report
AlexanderBogatko/TensorFlow_Keras_VAEGAN mentioned on GitHubtfSyntology: not harvested report
LynnHo/AttGAN-Tensorflow mentioned on GitHubtfSyntology: not harvested report
MariaPdg/fmri-reconstruction mentioned on GitHubpytorchSyntology: not harvested report
NanYi-hub/Deep-Generative-Network mentioned on GitHubSyntology: not harvested report
PrateekMunjal/Autoencoding-beyond-pixels-using-a-learned-similarity-metric mentioned on GitHubtfSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
Ram81/AC-VAEGAN-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
Umang-pandey/vae-gan-tf mentioned on GitHubtfSyntology: not harvested report
Vicent-xd/residual_encoding_net mentioned on GitHubtorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
adrienchaton/BERGAN mentioned on GitHubpytorchSyntology: not harvested report
andersbll/autoencoding_beyond_pixels mentioned on GitHubtorchMITSyntology: not harvested report
baon6052/VAE-GAN_Pegasus mentioned on GitHubSyntology: not harvested report
baudm/vaegan-celebs-keras mentioned on GitHubtfMITSyntology: 4 samples, 0 ran · 4 unverified report
clementchadebec/benchmark_VAE mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Variational Inference with Normalizing Flows (arXiv:1505.05770; that paper's own run record: 21 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
escuccim/vaegan-pytorch mentioned on GitHubpytorchSyntology: not harvested report
gm3g11/VAE_GAN_pytorch mentioned on GitHubpytorchSyntology: not harvested report
leoHeidel/vae-gan-tf2 mentioned on GitHubtfSyntology: not harvested report
manicman1999/Sword-GAN32 mentioned on GitHubSyntology: not harvested report
nguyenquangduc2000/AttGAN mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Invertible Conditional GANs for image editing (arXiv:1611.06355; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
oadonca/ANVAE mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NVAE: A Deep Hierarchical Variational Autoencoder (arXiv:2007.03898; that paper's own run record: 26 ran (of which 15 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 0 violated, 18 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
pranavbudhwant/ACVAEGAN mentioned on GitHubpytorchSyntology: not harvested report
pravn/vaegan mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
rishabhd786/VAE-GAN-PYTORCH mentioned on GitHubpytorchSyntology: not harvested report
ry85/VAE-GAN mentioned on GitHubpytorchSyntology: not harvested report
seangal/dcgan_vae_pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
timsainb/GAIA mentioned on GitHubtfSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
timsainb/Tensorflow-MultiGPU-VAE-GAN mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

13 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
2ran
5unverified

Licence: 7 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

PrateekMunjal/Autoencoding-beyond-pixels-using-a-learned-similarity-metric community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
denormalize_image in 5 papers Celeb-A/vae-gan.py ran · violated contract fingerprinted no licence file found · pointer only · 47cae7a59aef80c4 · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-22
image_meta Celeb-A/vae-gan.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · c2dc02c9e2165e5d · report fixture: signature image:ndarray/3/float · returned tuple · level recorded 2026-09-22
read_image in 73 papers Celeb-A/vae-gan.py unverified no licence file found · pointer only · 228f5d43c2691df1 · report
Vicent-xd/residual_encoding_net community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
mnist_inverse_transform mnist_ae.py ran MIT (permissive) · af1e887506d1fb55 · report fixture: signature imgs:ndarray/2/float, to_img:bool/0/bool · returned ndarray · level recorded 2026-09-26
baudm/vaegan-celebs-keras community (archive-listed) 4 samples, 0 ran · 4 unverified
build_graph in 20 papers vaegan/models.py unverified MIT (permissive) · fe8bd181101fc55b · report
create_models vaegan/models.py unverified MIT (permissive) · 27015033c4009152 · report
fit_models vaegan/training.py unverified MIT (permissive) · b829c4fcbfcea02d · report
mean_gaussian_negative_log_likelihood vaegan/losses.py unverified MIT (permissive) · 355977e8be1faa0d · report
pravn/vaegan community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
loss_function in 62 papers
census: 7 implementations from 6 papers, 7 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
modules_tied.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5c76b12c6eb7b27e · report fixture: signature recon_x:Tensor/2/float, x:Tensor/2/float, mu:Tensor/2/float, logvar:Tensor/2/float, bsz:int/0/int · returned Tensor · level recorded 2026-09-22
timsainb/GAIA community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 3 of 6, arg 1: rank 2, kind float, dtype float64
network.py ran · honoured contract fingerprinted no licence file found · pointer only · 24c29a6cb4733ecd · report fixture: signature X:ndarray/2/float · returned ndarray · level recorded 2026-09-22
norm_ax network.py ran · violated contract fingerprinted no licence file found · pointer only · 2f04e4472eba9e33 · report fixture: signature X:ndarray/2/float · returned ndarray · level recorded 2026-09-22
z_score network.py ran · honoured contract fingerprinted no licence file found · pointer only · bb7a8b5ac450e1f1 · report fixture: signature X:ndarray/2/float · returned ndarray · level recorded 2026-09-22
timsainb/Tensorflow-MultiGPU-VAE-GAN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get2d_deconv_output_size deconv.py ran MIT (permissive) · 9ba5d8704cc281c4 · report fixture: signature input_height:int/0/int, input_width:int/0/int, filter_height:int/0/int, filter_width:int/0/int, row_stride:int/0/int, col_stride:int/0/int, padding_type:str/0/str · returned tuple · level recorded 2026-09-26

Tasks

Translation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections