Methods › Computer Vision › Conditional Image-to-Image Translation Models › OASIS
OASIS
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:
-
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.
-
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).
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.
-
Matrix-Game: Interactive World Foundation Model 23 Jun 2025 · 1 repository · arXiv:2506.18701
-
OASIS: Online Sample Selection for Continual Visual Instruction Tuning 27 May 2025 · 0 repositories · arXiv:2506.02011
-
Reconsider the Template Mesh in Deep Learning-based Mesh Reconstruction 21 May 2025 · 0 repositories · arXiv:2505.15285
-
FF-PNet: A Pyramid Network Based on Feature and Field for Brain Image Registration 8 May 2025 · 0 repositories · arXiv:2505.04938
-
SAM-Guided Robust Representation Learning for One-Shot 3D Medical Image Segmentation 29 Apr 2025 · 0 repositories · arXiv:2504.20501
-
Exploring Robustness of Cortical Morphometry in the presence of white matter lesions, using Diffusion Models for Lesion Filling 26 Mar 2025 · 0 repositories · arXiv:2503.20571
-
Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis 11 Mar 2025 · 1 repository · arXiv:2503.08741Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
OASIS: Order-Augmented Strategy for Improved Code Search 11 Mar 2025 · 0 repositories · arXiv:2503.08161Syntology 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Adaptive parameters identification for nonlinear dynamics using deep permutation invariant networks 20 Jan 2025 · 0 repositories · arXiv:2501.11350
-
OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes 1 Jan 2025 · 0 repositories · arXiv:2501.00962
-
How reproducible are data-driven subtypes of Alzheimer's disease atrophy? 29 Nov 2024 · 0 repositories · arXiv:2412.00160
-
OASIS: Open Agent Social Interaction Simulations with One Million Agents 18 Nov 2024 · 1 repository · arXiv:2411.11581Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
Online Test of a Neural Network Deep Convection Parameterization in ARP-GEM1 29 Oct 2024 · 0 repositories · arXiv:2410.21920
-
SVS-GAN: Leveraging GANs for Semantic Video Synthesis 9 Sep 2024 · 0 repositories · arXiv:2409.06074
-
H-SGANet: Hybrid Sparse Graph Attention Network for Deformable Medical Image Registration 29 Aug 2024 · 0 repositories · arXiv:2408.16719
-
OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning 19 Jul 2024 · 1 repository · arXiv:2407.14653Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 1 pointer-only (licence)
-
Introducing VaDA: Novel Image Segmentation Model for Maritime Object Segmentation Using New Dataset 12 Jul 2024 · 0 repositories · arXiv:2407.09005
-
Local Methods with Adaptivity via Scaling 2 Jun 2024 · 0 repositories · arXiv:2406.00846
-
A Machine Learning Approach for Identifying Anatomical Biomarkers of Early Mild Cognitive Impairment 29 May 2024 · 0 repositories · arXiv:2407.00040
-
A light-weight rectangular decomposition large kernel convolution network for deformable medical image registration. 27 May 2024 · 1 repository
-
Computer aided diagnosis system for Alzheimers disease using principal component analysis and machine learning based approaches 15 Apr 2024 · 0 repositories · arXiv:2405.09553
-
EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration 16 Mar 2024 · 1 repository · arXiv:2403.11026
-
HyperPredict: Estimating Hyperparameter Effects for Instance-Specific Regularization in Deformable Image Registration 4 Mar 2024 · 1 repository · arXiv:2403.02069
-
3D Volumetric Super-Resolution in Radiology Using 3D RRDB-GAN 6 Feb 2024 · 0 repositories · arXiv:2402.04171
-
ADAPT: Alzheimer Diagnosis through Adaptive Profiling Transformers 12 Jan 2024 · 0 repositories · arXiv:2401.06349
-
OASIS: Offsetting Active Reconstruction Attacks in Federated Learning 23 Nov 2023 · 0 repositories · arXiv:2311.13739
-
Oasis: Data Curation and Assessment System for Pretraining of Large Language Models 21 Nov 2023 · 1 repository · arXiv:2311.12537
-
A Plug-and-Play Image Registration Network 6 Oct 2023 · 0 repositories · arXiv:2310.04297
-
Coupled Reconstruction of Cortical Surfaces by Diffeomorphic Mesh Deformation 21 Sep 2023 · 0 repositories
-
An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software 18 Aug 2023 · 0 repositories · arXiv:2308.09810
-
A behaviouristic approach to representing processes and procedures in the OASIS 2 ontology 30 Jun 2023 · 0 repositories · arXiv:2306.17514
-
Multi-task Collaborative Pre-training and Individual-adaptive-tokens Fine-tuning: A Unified Framework for Brain Representation Learning 20 Jun 2023 · 0 repositories · arXiv:2306.11378
-
The Ontology for Agents, Systems and Integration of Services: OASIS version 2 14 Jun 2023 · 0 repositories · arXiv:2306.10061
-
MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts 18 May 2023 · 1 repository · arXiv:2305.10799
-
OASIS: Automated Assessment of Urban Pedestrian Paths at Scale 4 Mar 2023 · 0 repositories · arXiv:2303.02287
-
Recurrence With Correlation Network for Medical Image Registration 5 Feb 2023 · 1 repository · arXiv:2302.02283
-
Application of Unsupervised Domain Adaptation for Structural MRI Analysis 26 Dec 2022 · 0 repositories · arXiv:2212.12986
-
Modelling Business Agreements in the Multimodal Transportation Domain through Ontological Smart Contracts 5 Sep 2022 · 0 repositories · arXiv:2209.05463
-
Contrastive Brain Network Learning via Hierarchical Signed Graph Pooling Model 14 Jul 2022 · 0 repositories · arXiv:2207.07650
-
On Scaled Methods for Saddle Point Problems 16 Jun 2022 · 0 repositories · arXiv:2206.08303
-
Deformable Registration of Brain MR Images via a Hybrid Loss 28 Oct 2021 · 0 repositories · arXiv:2110.15027
-
Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans 11 Oct 2021 · 1 repository · arXiv:2110.04994Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
ImUnity: a generalizable VAE-GAN solution for multicenter MR image harmonization 14 Sep 2021 · 0 repositories · arXiv:2109.06756
-
Online Enhanced Semantic Hashing: Towards Effective and Efficient Retrieval for Streaming Multi-Modal Data 9 Sep 2021 · 1 repository · arXiv:2109.04260
-
Clinica: an open source software platform for reproducible clinical neuroscience studies 21 Jul 2021 · 1 repository · arXiv:2107.10256
-
OASIS: An Active Framework for Set Inversion 31 May 2021 · 0 repositories · arXiv:2105.15024
-
DDR-Net: Dividing and Downsampling Mixed Network for Diffeomorphic Image Registration 24 May 2021 · 0 repositories · arXiv:2105.11361
-
Automatic Assessment of Alzheimer's Disease Diagnosis Based on Deep Learning Techniques 18 May 2021 · 1 repository · arXiv:2105.08446
-
Data Augmentation with Variational Autoencoders and Manifold Sampling 25 Mar 2021 · 1 repository · arXiv:2103.13751
-
You Only Need Adversarial Supervision for Semantic Image Synthesis 8 Dec 2020 · 1 repository · arXiv:2012.04781Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 7 harvested samples) · 7 pointer-only (licence)
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.
Usage over time archive 2025-07-28
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
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