Methods › Computer Vision › Conditional Image-to-Image Translation Models › OASIS

OASIS

50 papers tagged archive 2025-07-28

Introduced by Vadim Sushko et al. in You Only Need Adversarial Supervision for Semantic Image Synthesis

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

OASIS is a GAN-based model to translate semantic label maps into realistic-looking images. The model builds on preceding work such as Pix2Pix and SPADE. OASIS introduces the following innovations:

  1. The method is not dependent on the perceptual loss, which is commonly used for the semantic image synthesis task. A VGG network trained on ImageNet is routinely employed as the perceptual loss to strongly improve the synthesis quality. The authors show that this perceptual loss also has negative effects: First, it reduces the diversity of the generated images. Second, it negatively influences the color distribution to be more biased towards ImageNet. OASIS eliminates the dependence on the perceptual loss by changing the common discriminator design: The OASIS discriminator segments an image into one of the real classes or an additional fake class. In doing so, it makes more efficient use of the label maps that the discriminator normally receives. This distinguishes the discriminator from the commonly used encoder-shaped discriminators, which concatenate the label maps to the input image and predict a single score per image. With the more fine-grained supervision through the loss of the OASIS discriminator, the perceptual loss is shown to become unnecessary.

  2. A user can generate a diverse set of images per label map by simply resampling noise. This is achieved by conditioning the spatially-adaptive denormalization module in each layer of the GAN generator directly on spatially replicated input noise. A side effect of this conditioning is that at inference time an image can be resampled either globally or locally (either the complete image changes or a restricted region in the image).

PaperSourceSee Code · boschresearch/OASIS

In Syntology about another paper, arXiv:2503.08161: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). About another paper: this answer is about arXiv:2503.08161, while the archive credits arXiv:2012.04781.

From the lookup's note on this name: The same name also belongs to the paper “OASIS: Open Agent Social Interaction Simulations with One Million Agents” (arXiv:2411.11581, 138 citations), which the lookup finds cited far more than the paper this answer is about (7 citations), so this answer may be about a different sense of the name. For arXiv:2411.11581: its page on this site · ask the lookup about it.

Origin paper of this answer, arXiv:2503.08161 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence). Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 50 · with a code link: 16 · where Syntology ran a sample: 5 (3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (5 of 50 tagged: 3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 50 of 50, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 77 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Registration8
Medical Image Registration6
Image Generation4
Semantic Segmentation4
Deep Learning3
Deformable Medical Image Registration3
Large Language Model3
Representation Learning3
Segmentation3
Attribute2
Binary Classification2
Federated Learning2
Image Segmentation2
Language Modeling2
Language Modelling2
Retrieval2
Active Learning1
All1
Anatomy1
Anomaly Detection1

Usage over time archive 2025-07-28

Papers per year tagged with OASIS: 2020 to 2025, peak 15 15 0 2020: 1 paper 2020 2021: 9 papers 2021 2022: 4 papers 2022 2023: 11 papers 2023 2024: 15 papers 2024 2025: 10 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (50 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Conditional Image-to-Image Translation Models

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