Closing the Reality Gap with Unsupervised Sim-to-Real Image Translation
Deep learning approaches have become the standard solution to many problems in computer vision and robotics, but obtaining sufficient training data in high enough quality is challenging, as human labor is error prone, time consuming, and expensive. Solutions based on simulation have become more popular in recent years, but the gap between simulation and reality is still a major issue. In this paper, we introduce a novel method for augmenting synthetic image data through unsupervised image-to-image translation by applying the style of real world images to simulated images with open source frameworks. The generated dataset is combined with conventional augmentation methods and is then applied to a neural network model running in real-time on autonomous soccer robots. Our evaluation shows a significant improvement compared to models trained on images generated entirely in simulation.
Code (0)
등록된 구현이 없습니다.
Tasks
Image-to-Image TranslationSemantic SegmentationTranslationUnsupervised Image-To-Image TranslationSimilar Papers 제목 키워드 기반
USIS: Unsupervised Semantic Image Synthesis
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-th…
Image GenerationImage-to-Image TranslationTranslationTowards conceptual generalization in the embedding space
Humans are able to conceive physical reality by jointly learning different facets thereof. To every pair of notions related to a perceived reality may correspond a mutual relation, which is a notion on its own, but one-l…
Machine TranslationRelationTranslationRL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real
Deep neural network based reinforcement learning (RL) can learn appropriate visual representations for complex tasks like vision-based robotic grasping without the need for manually engineering or prior learning a percep…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robotic Grasping+1Cross-Domain Object Detection Using Unsupervised Image Translation
Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods approaching the alignment of the interme…
Unsupervised Domain AdaptationAutonomous DrivingObject DetectionDomain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. Whi…
ARCDepth EstimationDepth PredictionDomain Adaptation+3