Papers › Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective...

Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now

28 Nov 2023CVPR 2024 1arXiv:2311.17138archive 2025-07-28

Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik, D. A. Forsyth, Anand Bhattad

Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a set of collections of generated images, prequalified to fool simple, signal-based classifiers into believing they are real. We then show that prequalified generated images can be identified reliably by classifiers that only look at geometric properties. We use three such classifiers. All three classifiers are denied access to image pixels, and look only at derived geometric features. The first classifier looks at the perspective field of the image, the second looks at lines detected in the image, and the third looks at relations between detected objects and shadows. Our procedure detects generated images more reliably than SOTA local signal based detectors, for images from a number of distinct generators. Saliency maps suggest that the classifiers can identify geometric problems reliably. We conclude that current generators cannot reliably reproduce geometric properties of real images.

PaperPDFConference PDFCodeCode 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 18 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 17 ran (17 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hanlinm2/projective-geometry officialmentioned on GitHubpytorchMITSyntology: 18 samples, 17 ran (0 instrument-failed) · 1 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.

Code Syntology ran Syntology

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

17ran
1unverified

Licence: 0 of the 18 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 hanlinm2/projective-geometry. “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.

hanlinm2/projective-geometry official repository 18 samples, 17 ran (0 instrument-failed) · 1 unverified
compute_roc_curve prequalifier/prequalifier_test_helpers.py ran fingerprinted MIT (permissive) · a026c2d9978681cf · report fixture: signature all_labels:ndarray/1/int, all_generated_probs:ndarray/1/float · returned tuple · level recorded 2026-09-24
create_model in 163 papers line_segment/lines_model.py ran MIT (permissive) · a945396ca0b16803 · report fixture: signature target_device:device/0/? · returned ClassificationPointNet · level recorded 2026-09-24
create_model in 163 papers perspective_fields/fields_model.py ran MIT (permissive) · f3c36d02045cfbc2 · report fixture: signature target_device:device/0/? · returned FieldsClassifier · level recorded 2026-09-24
evaluate_on_dataloader prequalifier/prequalifier_test_helpers.py ran MIT (permissive) · 949786004f8eb80c · report fixture: signature model:callable/0/?, test_dataloader:list/1/tuple · returned tuple · level recorded 2026-09-24
get_recent_timestamp_dataloaders prequalifier/prequalifier_dataset.py ran MIT (permissive) · eb72ead7b49746e2 · report fixture: signature recent_timestamp_paths:dict/0/?, class_to_idx:dict/0/? · returned dict · level recorded 2026-09-24
get_test_dataloaders line_segment/lines_dataset.py ran MIT (permissive) · 7240b9840ca5e27e · report fixture: signature test_image_paths:list/1/str, unconfident_image_paths:list/1/str, misclassified_image_paths:list/1/str, image_path_to_lines:dict/0/?, class_to_idx:dict/0/? · returned tuple · level recorded 2026-09-24
get_test_dataloaders perspective_fields/fields_dataset.py ran MIT (permissive) · a52857a6650be07a · report fixture: signature test_image_paths:list/1/str, unconfident_image_paths:list/1/str, misclassified_image_paths:list/1/str, class_to_idx:dict/0/? · returned tuple · level recorded 2026-09-24
get_test_dataloaders prequalifier/prequalifier_dataset.py ran MIT (permissive) · 627f7f54e5d786a4 · report fixture: signature test_image_paths:list/1/str, unconfident_image_paths:list/1/str, misclassified_image_paths:list/1/str, class_to_idx:dict/0/? · returned tuple · level recorded 2026-09-24
get_train_dataloaders line_segment/lines_dataset.py ran MIT (permissive) · 6e612f3f3508395b · report fixture: signature train_image_paths:list/1/str, val_image_paths:list/1/str, image_path_to_lines:dict/0/?, class_to_idx:dict/0/? · returned tuple · level recorded 2026-09-24
get_train_dataloaders perspective_fields/fields_dataset.py ran MIT (permissive) · 59469a924d17ca67 · report fixture: signature train_image_paths:list/1/str, val_image_paths:list/1/str, class_to_idx:dict/0/? · returned tuple · level recorded 2026-09-24
load_all_paths line_segment/lines_path_helpers.py ran MIT (permissive) · f6bbfd4b67f32c83 · report fixture: signature base_path:str/0/str, data_paths:list/1/str · returned tuple · level recorded 2026-09-24
load_model in 479 papers line_segment/lines_model.py ran MIT (permissive) · 6b419f2ecfa7997a · report fixture: signature target_device:str/0/str, path_to_checkpoint:str/0/str · returned ClassificationPointNet · level recorded 2026-09-24
load_model in 479 papers perspective_fields/fields_model.py ran MIT (permissive) · bde9121fab9d6344 · report fixture: signature target_device:str/0/str, path_to_checkpoint:str/0/str · returned FieldsClassifier · level recorded 2026-09-24
load_outdoor_problem_paths line_segment/lines_path_helpers.py ran MIT (permissive) · c56c6c235242c726 · report fixture: signature base_path:str/0/str · returned list · level recorded 2026-09-24
load_recent_timestamp_paths prequalifier/prequalifier_path_helpers.py ran MIT (permissive) · f372edd1805aaa57 · report fixture: signature base_path:str/0/str, recent_timestamp_data_paths:list/1/str, category:str/0/str · returned dict · level recorded 2026-09-24
remove_problem_paths line_segment/lines_path_helpers.py ran MIT (permissive) · 45dd68d819a5dbf6 · report fixture: signature list_of_paths:list/1/list, base_path:str/0/str, category:str/0/str · returned list · level recorded 2026-09-24
timestamp_paths_from_data_paths prequalifier/prequalifier_path_helpers.py ran MIT (permissive) · 4ba2962f643eb701 · report fixture: signature base_path:str/0/str, data_paths:list/1/str · returned dict · level recorded 2026-09-24
load_model in 479 papers prequalifier/prequalifier_model.py unverified MIT (permissive) · f9e6838b930e3168 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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