Papers › Improved Precision and Recall Metric for Assessing Generative Models
Improved Precision and Recall Metric for Assessing Generative Models
Tuomas Kynkäänniemi, Tero Karras, Samuli Laine, Jaakko Lehtinen, Timo Aila
The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research. We present an evaluation metric that can separately and reliably measure both of these aspects in image generation tasks by forming explicit, non-parametric representations of the manifolds of real and generated data. We demonstrate the effectiveness of our metric in StyleGAN and BigGAN by providing several illustrative examples where existing metrics yield uninformative or contradictory results. Furthermore, we analyze multiple design variants of StyleGAN to better understand the relationships between the model architecture, training methods, and the properties of the resulting sample distribution. In the process, we identify new variants that improve the state-of-the-art. We also perform the first principled analysis of truncation methods and identify an improved method. Finally, we extend our metric to estimate the perceptual quality of individual samples, and use this to study latent space interpolations.
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):
get_harvested_code_for_paper(arxiv_id="1904.06991")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1904.06991", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1904.06991")
Code
Syntology 42 code samples harvested from 9 repositories linked to this paper: 30 ran (of which 12 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 1 violated, 14 with no contract checked; 10 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 4 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 38 samples from 8 repositories, 29 ran (19 with no instrument failure; 10 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.
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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.
Code Syntology ran Syntology
42 samples harvested: 30 ran (of which 12 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 1 violated, 14 with no contract checked; 10 where Syntology's instrument failed) · 12 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.
Licence: 25 of the 42 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 9 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.
5116b2e12b5213dd · report
fixture: returned ManifoldEstimator · level recorded 2026-09-22 24bf8c4eb19aecea · report
5339fe677f2a8aa3 · report
cb6d8f1a0fd320be · report
063f56b6465178ad · report
fixture: returned FileNames · level recorded 2026-09-22 f1bd04eed1f7e173 · report
fixture: returned IPR · level recorded 2026-09-22 c10080ea2e34a27c · report
fixture: returned ImageFolder · level recorded 2026-09-22 88c7b603b76960ad · report
fixture: signature manifold_ref:ManifoldRef/0/?, feats_subject:ndarray/2/float, desc:str/0/str · returned float64 · level recorded 2026-09-22 462603bdd8ffe544 · report
fixture: signature X:ndarray/2/float, Y:ndarray/2/float · returned ndarray · level recorded 2026-09-22 321ebed484cb3298 · report
fixture: signature distances:ndarray/2/float, k:int/0/int · returned ndarray · level recorded 2026-09-22 bcc716018b80b027 · report
fixture: signature np_array:ndarray/1/float, k:int/0/int · returned float32 · level recorded 2026-09-22 07bb109dd6cac3c5 · report
fixture: signature manifold_real:ManifoldReal/0/?, feat_subject:ndarray/2/float · returned float · level recorded 2026-09-22 43a458427eb4927c · report
64368fff5c6334de · report
fixture: returned ImageDataset · level recorded 2026-09-22 5bee49623aae7bf9 · report
fixture: returned feature_extractor · level recorded 2026-09-22 8514f2c85dc29786 · report
fixture: returned precision_and_recall · level recorded 2026-09-22 8985988572ef4703 · report
fixture: signature v1:ndarray/1/float, v2:ndarray/1/float · returned float64 · level recorded 2026-09-24 739a22fef98ba093 · report
fixture: signature array:ndarray/2/float, amount:int/0/int · returned ndarray · level recorded 2026-09-22 934af065bd096a31 · report
fixture: signature loc:str/0/str, flip:bool/0/bool, suffix:str/0/str · returned ndarray · level recorded 2026-09-24 8b8e982a58d7c4bd · report
fixture: returned PrecisionRecall · level recorded 2026-09-22 5636e68117082a03 · report
31d95e8ba2daecb1 · report
fixture: returned DistanceBlock · level recorded 2026-09-22 323cbfbab4a149aa · report
fixture: returned ManifoldEstimator · level recorded 2026-09-22 14c485bafef2920e · report
fixture: signature U:EagerTensor/2/float, V:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 b3cb1184b1155ae5 · report
8e2d8c2ab95b9ced · report
fixture: signature U:Tensor/2/float, V:Tensor/2/float · returned Tensor · level recorded 2026-09-22 6c9ddbe660f0c2da · report
fixture: signature dataloader:DataLoader/0/?, num_channels:int/0/int, num_samples:int/0/int, model:callable/0/? · returned Tensor · level recorded 2026-09-22 b24b104ab2fc127d · report
fixture: signature ref_features:Tensor/2/float, eval_features:Tensor/2/float, nhood_sizes:list/1/int, row_batch_size:int/0/int, col_batch_size:int/0/int · returned dict · level recorded 2026-09-22 d6d787dc36eccdbb · report
d4b397f131e3cb0d · report
0920b80eb6e4e57f · report
fixture: signature features_1:Tensor/2/float, features_2:Tensor/2/float, batch_size:int/0/int · returned Tensor · level recorded 2026-09-22 7d555d449583cad9 · report
fixture: signature features_1:Tensor/2/float, features_2:Tensor/2/float, batch_size:int/0/int · returned Tensor · level recorded 2026-09-22 fe34b19b6900c3ca · report
fixture: signature features_1:Tensor/2/float, features_2:Tensor/2/float, neighborhood:int/0/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-22 e0cea3ed105c7a3d · report
fixture: signature name:str/0/str, kwargs:dict/0/? · returned bool · level recorded 2026-09-22 fd7ffba6bfa9140c · report
034a66af56d59bf1 · report
e51e3d0dd80555f0 · report
3a19d7da570f0451 · report
fixture: returned IPR · level recorded 2026-09-22 3cf0aadecce9d196 · report
fixture: returned ImageFolder · level recorded 2026-09-22 af985ecf236605b0 · report
fixture: signature X:ndarray/2/float, Y:ndarray/2/float · returned ndarray · level recorded 2026-09-22 d4d53047a22471be · report
fixture: signature image_dir_or_fnames:list/1/str, image_size:int/0/int, batch_size:int/0/int, num_workers:int/0/int, num_samples:int/0/int · returned DataLoader · level recorded 2026-09-22 9f1f8858820c945f · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
8 sibling assemblies for Improved Precision and Recall Metric (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 4 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- knn_precision_recall_features entry · level 0 · unverified ·
b3cb1184b1155ae5 - DistanceBlock helper · level 1 · ran ·
31d95e8ba2daecb1 - ManifoldEstimator helper · level 1 · ran ·
323cbfbab4a149aa - batch_pairwise_distances helper · level 1 · ran · honoured contract ·
14c485bafef2920e
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 5 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- compute_precision_and_recall entry · level 0 · unverified ·
d4b397f131e3cb0d - get_features helper · level 1 · ran · honoured contract ·
6c9ddbe660f0c2da - knn_precision_recall_features metric · level 1 · ran · our draft was wrong ·
b24b104ab2fc127d - ManifoldEstimator model · level 0 · unverified ·
d6d787dc36eccdbb - batch_pairwise_distances helper · level 1 · ran · honoured contract ·
8e2d8c2ab95b9ced
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 7 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- prc_features_to_metric entry · level 0 · unverified ·
034a66af56d59bf1 - calculate_precision_recall_full helper · level 0 · unverified ·
fd7ffba6bfa9140c - calculate_precision_recall_part helper · level 1 · ran · our draft was wrong ·
fe34b19b6900c3ca - get_kwarg helper · level 1 · ran · violated contract ·
e0cea3ed105c7a3d - vprint helper · level 0 · unverified ·
e51e3d0dd80555f0 - calc_cdist_full helper · level 1 · ran · our draft was wrong ·
0920b80eb6e4e57f - calc_cdist_part helper · level 1 · ran · our draft was wrong ·
7d555d449583cad9
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 4 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- knn_precision_recall_features entry · level 0 · unverified ·
cb6d8f1a0fd320be - DistanceBlock helper · level 0 · unverified ·
24bf8c4eb19aecea - ManifoldEstimator metric · level 1 · ran ·
5116b2e12b5213dd - batch_pairwise_distances helper · level 0 · unverified ·
5339fe677f2a8aa3
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- precision_and_recall entry · level 1 · ran ·
8514f2c85dc29786 - feature_extractor helper · level 1 · ran ·
5bee49623aae7bf9 - ImageDataset helper · level 1 · ran ·
64368fff5c6334de
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 9 bricks; individually on a fixture: 8 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- IPR entry · level 1 · ran ·
f1bd04eed1f7e173 - compute_metric metric · level 1 · ran · our draft was wrong ·
88c7b603b76960ad - compute_pairwise_distances helper · level 1 · ran · honoured contract ·
462603bdd8ffe544 - distances2radii helper · level 1 · ran; the contract check could not run (RAISES) ·
321ebed484cb3298 - get_custom_loader helper · level 0 · unverified ·
43a458427eb4927c - realism helper · level 1 · ran · our draft was wrong ·
07bb109dd6cac3c5 - get_kth_value helper · level 1 · ran; the contract check could not run (RAISES) ·
bcc716018b80b027 - FileNames helper · level 1 · ran ·
063f56b6465178ad - ImageFolder helper · level 1 · ran ·
c10080ea2e34a27c
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- PrecisionRecall entry · level 1 · ran ·
8b8e982a58d7c4bd - Metric helper · level 0 · unverified ·
5636e68117082a03
harvested Assembly for Improved Precision and Recall Metric (graph method: Improved Precision and Recall Metric). 9 bricks; individually on a fixture: 8 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- IPR entry · level 1 · ran ·
3a19d7da570f0451 - compute_metric metric · level 0 · unverified ·
9f1f8858820c945f - compute_pairwise_distances helper · level 1 · ran · honoured contract ·
af985ecf236605b0 - distances2radii helper · level 1 · ran; the contract check could not run (RAISES) ·
321ebed484cb3298 - get_custom_loader helper · level 1 · ran · our draft was wrong ·
d4d53047a22471be - realism metric · level 1 · ran · our draft was wrong ·
07bb109dd6cac3c5 - get_kth_value helper · level 1 · ran; the contract check could not run (RAISES) ·
bcc716018b80b027 - FileNames helper · level 1 · ran ·
063f56b6465178ad - ImageFolder helper · level 1 · ran ·
3cf0aadecce9d196
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1904.06991") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | FFHQ | StyleGAN (no instance norm) | FID | 4.16 | #3 of 12 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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