The image filename is associated with the paper "Mirrored-Human: Reconstructing 3D Human Pose and Shape from a Single Image with a Mirror" .
The researchers developed a method to use mirror reflections to resolve the depth ambiguity inherent in single-view 3D human mesh recovery. TeenMarvel_Lili-Mesh-Mirror-004.jpg
The "TeenMarvel" part of the filename refers to a specific sub-collection or source of images used to build their comprehensive evaluation and training sets. You can find more details and the official implementation on their Mirrored-Human GitHub repository . The image filename is associated with the paper
Qi Fang, Qing Shuai, Junting Dong, Hujun Bao, and Xiaowei Zhou. Conference: CVPR 2021 (Oral). You can find more details and the official
The image is part of their Mirrored-Human dataset , which consists of diverse images of people in front of mirrors, specifically annotated to help the model learn from both the direct view and the reflected view.
Mirrored-Human: Reconstructing 3D Human Pose and Shape from a Single Image with a Mirror.
This research was presented at (Conference on Computer Vision and Pattern Recognition) and focuses on reconstructing 3D human meshes by leveraging the additional viewpoints provided by mirrors in a single image. Key Paper Details:
Not a member yet? Register now
Are you a member? Login now