Synthetic-to-Real Translation

55 papers with code • 4 benchmarks • 5 datasets

Synthetic-to-real translation is the task of domain adaptation from synthetic (or virtual) data to real data.

( Image credit: CYCADA )


Use these libraries to find Synthetic-to-Real Translation models and implementations

Most implemented papers

Learning to Adapt Structured Output Space for Semantic Segmentation

wasidennis/AdaptSegNet CVPR 2018

In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation.

Domain Adaptation for Structured Output via Discriminative Patch Representations

wasidennis/AdaptSegNet ICCV 2019

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks.

Diverse Image-to-Image Translation via Disentangled Representations

HsinYingLee/DRIT ECCV 2018

Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time.

Virtual to Real Reinforcement Learning for Autonomous Driving

rahul263-stack/Self-Driving-Car 13 Apr 2017

To our knowledge, this is the first successful case of driving policy trained by reinforcement learning that can adapt to real world driving data.

FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation

stu92054/Domain-adaptation-on-segmentation 8 Dec 2016

In this paper, we introduce the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems.

CyCADA: Cycle-Consistent Adversarial Domain Adaptation

jhoffman/cycada_release ICML 2018

Domain adaptation is critical for success in new, unseen environments.

Bidirectional Learning for Domain Adaptation of Semantic Segmentation

liyunsheng13/BDL CVPR 2019

In this paper, we propose a novel bidirectional learning framework for domain adaptation of segmentation.

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

layumi/Seg-Uncertainty 8 Mar 2020

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation.

DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation

lhoyer/DAFormer CVPR 2022

It improves the state of the art by 10. 8 mIoU for GTA-to-Cityscapes and 5. 4 mIoU for Synthia-to-Cityscapes and enables learning even difficult classes such as train, bus, and truck well.