Our latest work "Neural Texture Puppeteer" is published at https://openaccess.thecvf.com/content/WACV2024W/CV4Smalls/html/Waldmann_Neural_Texture_Puppeteer_A_Framework_for_Neural_Geometry_and_Texture_WACVW_2024_paper.html

As a base we make use of "Neural Puppeteer", an efficient and flexible neural rendering pipeline https://openaccess.thecvf.com/content/ACCV2022/html/Giebenhain_Neural_Puppeteer_Keypoint-Based_Neural_Rendering_of_Dynamic_Shapes_ACCV_2022_paper.html

Our key idea is to disentangle texture and geometry.

We show with twelve distinct synthetic cow textures that the new pipeline can be used in a downstream task to identify individuals.

#NeTePu #NePu #WACV #WACV24 #computervision @unikonstanz #CBehav #NeuralRendering #ReIdentification

Our latest work "Neural Puppeteer" is published at https://link.springer.com/chapter/10.1007/978-3-031-26316-3_15.

We estimate 3D keypoints from multi-view silhouettes only, using our inverse neural rendering pipeline. In this way our 3D keypoint estimation is robust against transformations that leave silhouettes unchanged like texture and lighting.

#NePu #NeuralRendering #PoseEstimation #3dpose #computervision #CBehav #UniKonstanz