Papers › Learning to generate line drawings that convey geometry and semantics

Learning to generate line drawings that convey geometry and semantics

23 Mar 2022CVPR 2022 1arXiv:2203.12691archive 2025-07-28

Caroline Chan, Fredo Durand, Phillip Isola

This paper presents an unpaired method for creating line drawings from photographs. Current methods often rely on high quality paired datasets to generate line drawings. However, these datasets often have limitations due to the subjects of the drawings belonging to a specific domain, or in the amount of data collected. Although recent work in unsupervised image-to-image translation has shown much progress, the latest methods still struggle to generate compelling line drawings. We observe that line drawings are encodings of scene information and seek to convey 3D shape and semantic meaning. We build these observations into a set of objectives and train an image translation to map photographs into line drawings. We introduce a geometry loss which predicts depth information from the image features of a line drawing, and a semantic loss which matches the CLIP features of a line drawing with its corresponding photograph. Our approach outperforms state-of-the-art unpaired image translation and line drawing generation methods on creating line drawings from arbitrary photographs. For code and demo visit our webpage carolineec.github.io/informative_drawings

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="2203.12691")

Code

Syntology Ran 4 of 18 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong.

By repository: official repository: 18 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

carolineec/informative-drawings 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; 4 ran; 0 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
14unverified

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 carolineec/informative-drawings. “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.

gram_matrix carolineec/informative-drawings/utils_pl.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 430c582cd8bbb1df · report
init_net carolineec/informative-drawings/networks.py official repository ran · our draft was wrong MIT (permissive) · 10fdae626d954364 · report
is_image_file carolineec/informative-drawings/dataset.py official repository ran · violated contract MIT (permissive) · 59848503040bbdac · report
unpickle carolineec/informative-drawings/dataset.py official repository ran · our draft was wrong MIT (permissive) · 80b795d920e2967a · report
add_margin carolineec/informative-drawings/base_dataset.py official repository unverified MIT (permissive) · 2623c33654e1da14 · report
channel2width carolineec/informative-drawings/utils.py official repository unverified MIT (permissive) · c5f6a77d35d36163 · report
createNRandompatches carolineec/informative-drawings/utils.py official repository unverified MIT (permissive) · adce554a3dd42bae · report
get_norm_layer carolineec/informative-drawings/networks.py official repository unverified MIT (permissive) · 30190c576dd53b28 · report
get_params carolineec/informative-drawings/base_dataset.py official repository unverified MIT (permissive) · d80e86b2b7fb857b · report
get_scheduler carolineec/informative-drawings/networks.py official repository unverified MIT (permissive) · 78865ef3023c58ad · report
get_transform carolineec/informative-drawings/base_dataset.py official repository unverified MIT (permissive) · e045b7099733bf40 · report
load_image carolineec/informative-drawings/utils_pl.py official repository unverified MIT (permissive) · 7d363fa05027abd2 · report
make_dataset carolineec/informative-drawings/dataset.py official repository unverified MIT (permissive) · 5c701194ea1b715a · report
normalize_batch carolineec/informative-drawings/utils_pl.py official repository unverified MIT (permissive) · 9a49c7512264eb68 · report
tensor2im carolineec/informative-drawings/util/util.py official repository unverified MIT (permissive) · 3c356092464d28e0 · report
tensor2image carolineec/informative-drawings/utils.py official repository unverified MIT (permissive) · 0ee3f9ee92d8a8c6 · report
tensor2imv2 carolineec/informative-drawings/util/util.py official repository unverified MIT (permissive) · 1590350b5aa06dc4 · report
tensor2label carolineec/informative-drawings/util/util.py official repository unverified MIT (permissive) · 60597ae0bacbcfc2 · report

Tasks

Image-to-Image TranslationTranslationUnsupervised Image-To-Image Translation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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