Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
CVPR(2020)
摘要
Our goal is to capture the pose of neuroscience model organisms, without using any manual supervision, to be able to study how neural circuits orchestrate behaviour. Human pose estimation attains remarkable accuracy when trained on real or simulated datasets consisting of millions of frames. However, for many applications simulated models are unrealistic and real training datasets with comprehensive annotations do not exist. We address this problem with a new sim2real domain transfer method. Our key contribution is the explicit and independent modeling of appearance, shape and poses in an unpaired image translation framework. Our model lets us train a pose estimator on the target domain by transferring readily available body keypoint locations from the source domain to generated target images. We compare our approach with existing domain transfer methods and demonstrate improved pose estimation accuracy on Drosophila melanogaster (fruit fly), Caenorhabditis elegans (worm) and Danio rerio (zebrafish), without requiring any manual annotation on the target domain and despite using simplistic off-the-shelf animal characters for simulation, or simple geometric shapes as models. Our new datasets, code, and trained models will be published to support future neuroscientific studies.
更多查看译文
关键词
deformation-aware unpaired image translation,laboratory animals,synthetic training datasets,neuroscience model organisms,neural circuits,human pose estimation,sim2real domain transfer method,unpaired image translation framework,domain transfer methods,estimation accuracy,body keypoint locations,target image generation,Caenorhabditis elegans,Danio rerio,zebrafish,neuroscientific studies,computer vision,Drosophila melanogaster
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络