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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2311.17138")

Code

Syntology Ran 17 of 18 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 17 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 17 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hanlinm2/projective-geometry officialmentioned on GitHubpytorchMIT 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; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

compute_roc_curve hanlinm2/projective-geometry/prequalifier/prequalifier_test_helpers.py official repository ran MIT (permissive) · a026c2d9978681cf · report
create_model hanlinm2/projective-geometry/line_segment/lines_model.py official repository ran MIT (permissive) · a945396ca0b16803 · report
create_model hanlinm2/projective-geometry/perspective_fields/fields_model.py official repository ran MIT (permissive) · f3c36d02045cfbc2 · report
evaluate_on_dataloader hanlinm2/projective-geometry/prequalifier/prequalifier_test_helpers.py official repository ran MIT (permissive) · 949786004f8eb80c · report
get_recent_timestamp_dataloaders hanlinm2/projective-geometry/prequalifier/prequalifier_dataset.py official repository ran MIT (permissive) · eb72ead7b49746e2 · report
get_test_dataloaders hanlinm2/projective-geometry/line_segment/lines_dataset.py official repository ran MIT (permissive) · 7240b9840ca5e27e · report
get_test_dataloaders hanlinm2/projective-geometry/perspective_fields/fields_dataset.py official repository ran MIT (permissive) · a52857a6650be07a · report
get_test_dataloaders hanlinm2/projective-geometry/prequalifier/prequalifier_dataset.py official repository ran MIT (permissive) · 627f7f54e5d786a4 · report
get_train_dataloaders hanlinm2/projective-geometry/line_segment/lines_dataset.py official repository ran MIT (permissive) · 6e612f3f3508395b · report
get_train_dataloaders hanlinm2/projective-geometry/perspective_fields/fields_dataset.py official repository ran MIT (permissive) · 59469a924d17ca67 · report
load_all_paths hanlinm2/projective-geometry/line_segment/lines_path_helpers.py official repository ran MIT (permissive) · f6bbfd4b67f32c83 · report
load_model hanlinm2/projective-geometry/line_segment/lines_model.py official repository ran MIT (permissive) · 6b419f2ecfa7997a · report
load_model hanlinm2/projective-geometry/perspective_fields/fields_model.py official repository ran MIT (permissive) · bde9121fab9d6344 · report
load_outdoor_problem_paths hanlinm2/projective-geometry/line_segment/lines_path_helpers.py official repository ran MIT (permissive) · c56c6c235242c726 · report
load_recent_timestamp_paths hanlinm2/projective-geometry/prequalifier/prequalifier_path_helpers.py official repository ran MIT (permissive) · f372edd1805aaa57 · report
remove_problem_paths hanlinm2/projective-geometry/line_segment/lines_path_helpers.py official repository ran MIT (permissive) · 45dd68d819a5dbf6 · report
timestamp_paths_from_data_paths hanlinm2/projective-geometry/prequalifier/prequalifier_path_helpers.py official repository ran MIT (permissive) · 4ba2962f643eb701 · report
load_model hanlinm2/projective-geometry/prequalifier/prequalifier_model.py official repository 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